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

    Neuronpedia

    INDEX
    Explanations

    example output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     либо
    0.81
     خاصيه
    0.78
     loopholes
    0.77
     Акы
    0.76
     definitivamente
    0.73
     imediatamente
    0.72
    >/</
    0.72
    了吗
    0.71
     있는지
    0.71
     обов
    0.70
    POSITIVE LOGITS
     Example
    2.20
     example
    2.15
    Example
    2.08
    example
    2.03
     imagine
    2.02
     hypothetical
    2.01
    假設
    1.98
     Suppose
    1.97
     Illust
    1.93
    假设
    1.93
    Act Density 0.916%

    No Known Activations