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

    Neuronpedia

    INDEX
    Explanations

    functions and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    1.31
    n
    1.02
    न
    0.82
    h
    0.76
     яка
    0.74
     that
    0.74
    с
    0.71
    منٹ
    0.71
     shoulder
    0.70
     at
    0.70
    POSITIVE LOGITS
    .
    1.34
    يرا
    0.94
     comprobar
    0.82
    д
    0.78
    .}$
    0.77
    ходе
    0.76
    ow
    0.75
    ברו
    0.75
    смотреть
    0.75
    дят
    0.73
    Act Density 0.013%

    No Known Activations