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

    Neuronpedia

    INDEX
    Explanations

    protected characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ı
    1.39
    "
    1.34
    }";
    1.06
    ;
    1.05
     agreg
    1.04
    は
    1.00
     seria
    0.94
     as
    0.94
     destac
    0.93
     allí
    0.92
    POSITIVE LOGITS
    ד
    1.45
    д
    1.30
    н
    1.20
    ל
    1.19
     for
    1.18
    יש
    1.05
    י
    1.05
    ن
    1.01
    د
    1.00
    น
    0.97
    Act Density 0.015%

    No Known Activations