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

    Neuronpedia

    INDEX
    Explanations

    community -

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     talking
    0.39
    ullo
    0.36
    ully
    0.36
     marm
    0.36
     クリ
    0.36
    PolicyQuery
    0.36
    nmid
    0.36
     Staff
    0.35
    楽
    0.35
    PON
    0.35
    POSITIVE LOGITS
     fork
    0.41
     FOM
    0.41
     башка
    0.38
    fqsen
    0.36
     брат
    0.36
    BUGFS
    0.36
    เจน
    0.35
     чер
    0.35
    ̉a
    0.35
    കാന്‍
    0.35
    Act Density 0.003%

    No Known Activations