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

    Neuronpedia

    INDEX
    Explanations

    punctuation and its marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     keywords
    0.44
    キーワード
    0.41
     videolar
    0.40
    vodu
    0.39
    中間
    0.39
    TGFuZ
    0.39
    ยายาม
    0.39
     buradan
    0.39
    Administrator
    0.38
    бори
    0.38
    POSITIVE LOGITS
     punctuation
    1.24
     punctu
    0.97
    punctuation
    0.87
     punct
    0.82
     commas
    0.80
     punctuated
    0.78
     exclamation
    0.77
     quotation
    0.76
     comma
    0.75
    comma
    0.71
    Act Density 0.026%

    No Known Activations