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

    Neuronpedia

    INDEX
    Explanations

    software as a service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    1.07
    我
    0.95
    م
    0.91
    सी
    0.84
    д
    0.82
    ه
    0.82
    数据
    0.82
    ب
    0.81
    إ
    0.78
    ك
    0.77
    POSITIVE LOGITS
    ﾞ
    0.84
    et
    0.84
     an
    0.81
    as
    0.79
    yra
    0.79
    F
    0.76
    uesday
    0.74
    iere
    0.73
    Hospital
    0.73
    ัน
    0.73
    Act Density 0.015%

    No Known Activations