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

    Neuronpedia

    INDEX
    Explanations

    one of the oldest/most/highest/largest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.85
    i
    1.73
    z
    1.59
     a
    1.55
    the
    1.53
    r
    1.46
    aing
    1.45
     the
    1.42
    ی
    1.41
    رے
    1.28
    POSITIVE LOGITS
    ில்
    1.28
     môžu
    1.27
     hundred
    1.26
    Hundred
    1.23
    多い
    1.20
    ட்டார்
    1.18
    個セット
    1.17
    螅
    1.16
     fleste
    1.14
    ীর
    1.13
    Act Density 0.048%

    No Known Activations