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

    Neuronpedia

    INDEX
    Explanations

    Arabic and English

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     belge
    0.54
     merah
    0.52
     日本製
    0.52
     rubble
    0.51
     homage
    0.50
     jeep
    0.50
     helplessly
    0.50
     europeos
    0.50
     rojo
    0.50
     ૧
    0.50
    POSITIVE LOGITS
     הה
    0.66
    the
    0.65
    الت
    0.64
     الت
    0.63
     الأ
    0.62
    الب
    0.61
     التد
    0.61
    The
    0.58
     الك
    0.58
     الج
    0.57
    Act Density 0.002%

    No Known Activations