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

    Neuronpedia

    INDEX
    Explanations

    expressions related to correctness and justification

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

    correctly notes or argues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Географиясе
    -0.43
    cop
    -0.36
    //{
    -0.35
     Cata
    -0.34
    ieste
    -0.34
    Życiorys
    -0.34
    tiens
    -0.33
    ToProps
    -0.33
    icordia
    -0.32
    xffffffff
    -0.32
    POSITIVE LOGITS
     rightly
    0.66
     rightfully
    0.64
     للمعارف
    0.63
     IBOutlet
    0.58
     HasFactory
    0.58
     للاسماء
    0.55
     estekak
    0.52
    LookAnd
    0.52
    脚注の使い方
    0.50
    getKeyCode
    0.50
    Act Density 0.221%

    No Known Activations