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

    Neuronpedia

    INDEX
    Explanations

    October and November dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.82
     a
    0.74
    ,
    0.70
     that
    0.70
     (
    0.66
     either
    0.65
     this
    0.63
    ↵↵
    0.59
     an
    0.59
     be
    0.59
    POSITIVE LOGITS
    ೆಂಟ್
    0.82
    ཊ
    0.79
    ၎
    0.79
     നിരവധി
    0.78
     Australien
    0.78
     tagReport
    0.76
    Razibul
    0.74
     PlayerSelector
    0.73
    Ꮐ
    0.73
    ཌ
    0.73
    Act Density 0.049%

    No Known Activations