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

    Neuronpedia

    INDEX
    Explanations

    questions or expressions indicating uncertainty or requests for clarification

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

    mathematical and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GIVEREF
    -0.56
    contentLoaded
    -0.55
    afficheront
    -0.53
    parsedMessage
    -0.52
     ddelweddau
    -0.52
    AutoScaleMode
    -0.52
    HasAnnotation
    -0.51
     ویکی‌پدیا
    -0.50
    таратура
    -0.49
    -0.48
    POSITIVE LOGITS
     Proposition
    0.43
    extAlignment
    0.42
     increí
    0.41
    Specyfikacja
    0.40
    ficulties
    0.39
     União
    0.39
    bước
    0.39
    aaral
    0.39
     foly
    0.38
     pérd
    0.37
    Act Density 0.000%

    No Known Activations