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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and inline math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.10
    i
    1.05
    ла
    0.93
     Neue
    0.84
    は
    0.79
    nö
    0.79
    تهم
    0.79
    تون
    0.78
    ت
    0.76
    لي
    0.76
    POSITIVE LOGITS
    )*
    0.80
    fitrión
    0.79
     dịp
    0.78
     הט
    0.75
     মতো
    0.75
     avión
    0.75
    на
    0.74
    (“
    0.72
    (
    0.71
    ↵↵
    0.71
    Act Density 0.000%

    No Known Activations