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

    Neuronpedia

    INDEX
    Explanations

    explaining processes or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ・
    0.20
    との
    0.20
    (\
    0.19
     অর্থাৎ
    0.18
    $(\
    0.18
    {\
    0.17
    arcía
    0.17
     based
    0.17
    vien
    0.17
    Based
    0.17
    POSITIVE LOGITS
    how
    0.22
    permission
    0.21
    golden
    0.21
    玩法
    0.19
    regulars
    0.19
    success
    0.18
    evil
    0.18
     nasıl
    0.18
    friction
    0.18
    hidden
    0.18
    Act Density 0.491%

    No Known Activations