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

    Neuronpedia

    INDEX
    Explanations

    sudden or mysterious disappearances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    1.19
     an
    0.95
    、
    0.87
    Y
    0.84
     concess
    0.82
    ों
    0.81
     to
    0.79
     for
    0.79
    ش
    0.79
     my
    0.77
    POSITIVE LOGITS
    g
    0.90
    ла
    0.84
    t
    0.83
    f
    0.81
    گاه
    0.80
    ся
    0.80
    েন
    0.76
    но
    0.76
    ية
    0.76
     disappearance
    0.76
    Act Density 0.007%

    No Known Activations