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

    Neuronpedia

    INDEX
    Explanations

    style variations and translations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    1.09
    ’
    0.79
    5
    0.78
    lar
    0.77
    א
    0.74
    6
    0.69
    ların
    0.69
    る
    0.69
    ING
    0.68
    יות
    0.68
    POSITIVE LOGITS
     스타일
    1.09
     estilo
    1.08
     стиль
    1.08
     STYLE
    1.01
     शैली
    0.98
    风格
    0.87
     styles
    0.86
    風格
    0.84
     estilos
    0.84
     style
    0.83
    Act Density 0.046%

    No Known Activations