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

    Neuronpedia

    INDEX
    Explanations

    SPY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ки
    1.10
    nable
    0.93
    кает
    0.93
    E
    0.92
    cura
    0.92
    na
    0.88
    г
    0.86
    χου
    0.85
    キスト
    0.84
    ness
    0.84
    POSITIVE LOGITS
     arn
    1.20
     thương
    1.19
     aswell
    1.14
     görm
    1.12
     মুহূর্তে
    1.12
    ăz
    1.10
    ỷ
    1.08
    恤
    1.07
     Nadine
    1.07
     rétro
    1.06
    Act Density 0.000%

    No Known Activations