Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    definitions and mathematical notation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical symbols and expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation (e.g. $\Delta, \mathcal{L}, \Gamma, (i,j)\in\mathcal{T}'(r)$)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cucchia
    -0.61
    cinhas
    -0.60
     métallique
    -0.60
    orini
    -0.59
     marinho
    -0.58
     crescere
    -0.58
    ianum
    -0.56
     réglable
    -0.56
     actuelle
    -0.55
     vestiti
    -0.54
    POSITIVE LOGITS
     M
    0.98
     F
    0.95
     Q
    0.93
     G
    0.93
     S
    0.92
     R
    0.92
     P
    0.91
     D
    0.89
     C
    0.88
     L
    0.88
    Act Density 0.876%

    No Known Activations