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

    Neuronpedia

    INDEX
    Explanations

    references to understanding and problem-solving processes

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

    [Verb] + out

    np_acts-logits-general · gemini-2.0-flash

    figure out / check out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.59
     صوتيه
    -0.56
    InteropServices
    -0.51
    #!/
    -0.51
    StoryboardSegue
    -0.47
     jsPsych
    -0.46
    Ons
    -0.46
    দ্ধ
    -0.43
     Jurí
    -0.42
    umbai
    -0.42
    POSITIVE LOGITS
     out
    2.91
    out
    2.14
     Out
    1.84
    Out
    1.81
     OUT
    1.76
    outs
    1.52
    OUT
    1.43
     outs
    1.40
    出
    1.21
    アウト
    1.18
    Act Density 0.281%

    No Known Activations