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

    Neuronpedia

    INDEX
    Explanations

    disposable items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이다
    0.70
    ۔
    0.70
    ה
    0.68
    며
    0.66
    О
    0.65
    ات
    0.63
    った
    0.63
     vòng
    0.63
    Κ
    0.63
    માં
    0.62
    POSITIVE LOGITS
    Disposable
    1.09
     Disposable
    1.09
    n
    1.01
     disposable
    0.82
    z
    0.78
    ur
    0.75
    de
    0.73
    y
    0.72
    f
    0.71
    ch
    0.68
    Act Density 0.001%

    No Known Activations