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

    Neuronpedia

    INDEX
    Explanations

    about what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kalau
    0.55
     tanggal
    0.49
    ﻭ
    0.49
     ذریع
    0.47
    jumpa
    0.46
    Pada
    0.46
    アンド
    0.46
    あえず
    0.46
    garakan
    0.45
     بیچ
    0.45
    POSITIVE LOGITS
    e
    0.50
    is
    0.46
     he
    0.46
     Af
    0.45
    о
    0.44
    o
    0.44
     observed
    0.44
     as
    0.43
    再次
    0.43
    нести
    0.43
    Act Density 0.001%

    No Known Activations