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

    Neuronpedia

    INDEX
    Explanations

    Ashkenazi Jewishsqlalchemy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    е
    0.65
    もら
    0.61
     আদাল
    0.60
    о
    0.59
    zysz
    0.59
    ы
    0.59
     في
    0.57
    取り
    0.57
     ಮಾಹಿತ
    0.57
    у
    0.57
    POSITIVE LOGITS
    i
    0.99
    지
    0.82
    ו
    0.78
    ]
    0.78
    ت
    0.78
    t
    0.76
    ic
    0.74
     that
    0.73
    鎿
    0.71
     Levant
    0.69
    Act Density 0.003%

    No Known Activations