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

    Neuronpedia

    INDEX
    Explanations

    allow dealerships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %
    0.48
    ong
    0.46
     figures
    0.45
    x
    0.45
     بش
    0.44
    oto
    0.43
    il
    0.43
     ป
    0.42
    {}",
    0.41
    OT
    0.41
    POSITIVE LOGITS
     pisan
    0.46
    addassa
    0.46
     выражения
    0.44
     trimestre
    0.43
    푞
    0.42
    樑
    0.42
    ስቃ
    0.42
     изменения
    0.42
    ಲು
    0.42
    ழிய
    0.42
    Act Density 0.000%

    No Known Activations