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

    Neuronpedia

    INDEX
    Explanations

    functions or systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.56
    in
    0.48
     opportunities
    0.44
    Opportunities
    0.44
    e
    0.43
    Post
    0.43
    ا
    0.43
     transformation
    0.43
    ُ
    0.43
    oid
    0.41
    POSITIVE LOGITS
    phalodes
    0.57
     andolan
    0.55
    скетбол
    0.53
    ড়িত
    0.52
     Towa
    0.51
    showinfo
    0.50
     ادي
    0.50
    ⚤
    0.49
     místě
    0.49
    रिडोर
    0.48
    Act Density 0.001%

    No Known Activations