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

    Neuronpedia

    INDEX
    Explanations

    can provide/offer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ется
    0.57
     Ocak
    0.57
    ن
    0.54
    ה
    0.52
    ె
    0.49
    ه
    0.48
    MENTS
    0.48
    oslash
    0.48
     março
    0.46
    િસ્
    0.45
    POSITIVE LOGITS
     खुशखबरी
    0.46
     adaptable
    0.45
    rl
    0.45
     harm
    0.43
     planar
    0.43
    ani
    0.43
     preventive
    0.43
    asy
    0.42
    uj
    0.42
     hjälp
    0.41
    Act Density 0.001%

    No Known Activations