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

    Neuronpedia

    INDEX
    Explanations

    Russian and Arabic script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.72
     racist
    0.63
     fusible
    0.62
     просты
    0.60
    reathe
    0.59
    icuously
    0.59
     இருந்த
    0.58
    kami
    0.57
     ראש
    0.55
    arily
    0.55
    POSITIVE LOGITS
    ме
    0.97
    و
    0.95
    ز
    0.95
    з
    0.90
    на
    0.88
    ات
    0.88
    ا
    0.88
    ور
    0.86
    یا
    0.83
    ра
    0.82
    Act Density 0.022%

    No Known Activations