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

    Neuronpedia

    INDEX
    Explanations

    numerical values indicating measurements or results

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

    Text followed by punctuation and numbers

    np_acts-logits-general · gemini-2.0-flash

    2.40:1 aspect ratio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.86
    :✨
    -0.68
    ISupport
    -0.68
    GraphicsUnit
    -0.68
     itſelf
    -0.63
    ContentAlignment
    -0.62
    xffffffff
    -0.62
    messageInfo
    -0.62
    قایناقلار
    -0.61
    انيف
    -0.60
    POSITIVE LOGITS
     Paglinawan
    0.66
    ())),
    0.59
    ()];
    0.59
    ()}>
    0.58
    ())))
    0.56
    ']))
    0.56
    ())));
    0.56
    )}(\
    0.56
    ()){
    0.55
    <>());
    0.53
    Act Density 0.315%

    No Known Activations