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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

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

    ordinal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    点此举报
    -0.74
    setVerticalGroup
    -0.71
    ruguay
    -0.70
    arangay
    -0.69
    mpagne
    -0.68
     desmotivaciones
    -0.68
    gucig
    -0.66
     ſever
    -0.65
     eſſ
    -0.60
    征詢我
    -0.60
    POSITIVE LOGITS
    .
    0.58
     Sixth
    0.52
     Third
    0.49
     Fifth
    0.49
    Sixth
    0.47
     sixth
    0.46
     Ninth
    0.45
    Third
    0.45
     fifth
    0.44
    Fifth
    0.44
    Act Density 0.007%

    No Known Activations