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

    Neuronpedia

    INDEX
    Explanations

    can be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.96
    ন
    0.95
    (
    0.93
    ات
    0.86
     gái
    0.84
    ভাবে
    0.82
    ंना
    0.81
    rante
    0.80
    1
    0.80
    مان
    0.79
    POSITIVE LOGITS
    c
    1.27
    g
    1.17
    ي
    1.02
     in
    1.00
     improb
    1.00
    i
    0.99
    SA
    0.98
    ла
    0.98
     disastrous
    0.98
    ได้
    0.97
    Act Density 0.002%

    No Known Activations