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

    Neuronpedia

    INDEX
    Explanations

    weaknesses:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nu
    0.91
    َ
    0.80
    de
    0.74
    ng
    0.70
    ll
    0.70
    ne
    0.70
    }\
    0.70
     It
    0.70
     Himachal
    0.67
    div
    0.65
    POSITIVE LOGITS
    ה
    1.02
    ע
    0.95
    ალი
    0.89
    at
    0.88
    ار
    0.88
    ב
    0.87
     weaknesses
    0.82
    א
    0.80
    ol
    0.79
    ності
    0.79
    Act Density 0.006%

    No Known Activations