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

    Neuronpedia

    INDEX
    Explanations

    statistical data and percentages related to health or safety outcomes

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

    amounts and frequencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kháu
    -0.50
     Réponses
    -0.47
    styrelsen
    -0.46
     Balance
    -0.45
    Попис
    -0.45
    quelize
    -0.44
    robo
    -0.44
     nakalista
    -0.44
     discipline
    -0.43
     reluctantly
    -0.43
    POSITIVE LOGITS
     parfois
    0.53
     addirittura
    0.52
     persino
    0.47
     akár
    0.47
     jopa
    0.47
     nawet
    0.45
     sometimes
    0.44
     fometimes
    0.43
    Sometimes
    0.42
    有时
    0.42
    Act Density 0.053%

    No Known Activations