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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation, particularly commas

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

    From to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OnTriggerEnter
    -0.49
     nakalista
    -0.42
    printStackTrace
    -0.35
    WriteLiteral
    -0.35
     PopupWindow
    -0.34
     Sand
    -0.34
    存于互联网档案馆
    -0.34
     arte
    -0.34
    日閲覧
    -0.34
    OfWork
    -0.34
    POSITIVE LOGITS
    Tembelea
    0.50
     Thier
    0.49
    évaluateur
    0.49
     compéti
    0.46
    Whatever
    0.46
    Wherever
    0.45
     hjer
    0.45
    industry
    0.44
    irsch
    0.44
     ProtoMessage
    0.43
    Act Density 0.011%

    No Known Activations