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

    Neuronpedia

    INDEX
    Explanations

    programming functions and their definitions

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

    user turn indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zurückge
    -0.37
     stå
    -0.32
     simply
    -0.31
    richTextPanel
    -0.30
    InSection
    -0.29
    LabelTagHelper
    -0.29
     seuls
    -0.29
     gebeurt
    -0.29
     fatica
    -0.29
    ictwa
    -0.29
    POSITIVE LOGITS
     Taktlose
    0.66
    Controllo
    0.63
     desmotivaciones
    0.62
     المعيارى
    0.58
    Географиясе
    0.57
    ViewImports
    0.57
     ویکی‌پدی
    0.55
    Hentet
    0.55
    ScopeManager
    0.53
     للاسماء
    0.53
    Act Density 0.008%

    No Known Activations