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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and exclamations in dialogue and quoted text

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.44
    \
    -0.40
     V
    -0.39
    ěte
    -0.39
     lanjut
    -0.39
    /
    -0.39
    アナ
    -0.39
     Kan
    -0.39
    kan
    -0.39
     luat
    -0.37
    POSITIVE LOGITS
     autorytatywna
    1.06
    :✨
    0.91
     كومونز
    0.80
    ngdoc
    0.76
    setVerticalGroup
    0.76
    ChildScrollView
    0.76
    TestingModule
    0.74
     canst
    0.71
     onAnimation
    0.71
     للاسماء
    0.70
    Act Density 0.184%

    No Known Activations