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

    Neuronpedia

    INDEX
    Explanations

    scientific method programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.91
    s
    1.91
    ar
    1.77
    h
    1.74
    ن
    1.73
    k
    1.72
    س
    1.72
    at
    1.67
    es
    1.65
    in
    1.63
    POSITIVE LOGITS
    ている
    1.33
    ০০০
    1.13
     спосо
    1.11
     pluripotent
    1.10
    뛰
    1.10
     differenti
    1.09
     Eurostile
    1.08
    မှုကို
    1.07
    ১৪
    1.05
    てください
    1.05
    Act Density 0.400%

    No Known Activations