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

    Neuronpedia

    INDEX
    Explanations

    works reliably, correctly, fast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.67
    I
    0.65
    ONU
    0.64
    management
    0.63
    are
    0.61
    IQ
    0.59
    contraction
    0.58
    noise
    0.57
    making
    0.57
    EQ
    0.57
    POSITIVE LOGITS
    ת
    0.79
    त
    0.68
     작동
    0.65
     Siempre
    0.61
    ט
    0.61
    ب
    0.60
     on
    0.60
     perangkat
    0.58
     explicado
    0.57
    ות
    0.56
    Act Density 0.053%

    No Known Activations