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

    Neuronpedia

    INDEX
    Explanations

    data field names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     réseau
    0.42
     gimnas
    0.41
     मनात
    0.41
    ٹ
    0.40
    ަރު
    0.39
     Schwier
    0.39
     peralatan
    0.39
     îng
    0.38
    雩
    0.38
     könnt
    0.38
    POSITIVE LOGITS
     ratio
    0.52
    ).
    0.49
    ),
    0.45
    );
    0.44
     percentage
    0.44
    ().
    0.42
     parameters
    0.41
    参数
    0.41
     bytes
    0.40
     absolute
    0.40
    Act Density 0.027%

    No Known Activations