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

    Neuronpedia

    INDEX
    Explanations

    system acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tions
    3.11
    to
    3.05
    tion
    3.05
    t
    2.67
    tr
    2.59
    ti
    2.55
    tan
    2.52
    tracks
    2.42
    times
    2.41
    type
    2.39
    POSITIVE LOGITS
    ن
    2.14
    ра
    2.09
    ح
    1.95
    ك
    1.95
    ς
    1.91
    بي
    1.88
    ̌
    1.85
    crever
    1.84
    ет
    1.80
    お金
    1.78
    Act Density 0.580%

    No Known Activations