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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yk
    -0.07
     gcd
    -0.06
     Carpenter
    -0.06
    anager
    -0.06
    Universal
    -0.06
    change
    -0.06
    [E
    -0.06
     wiel
    -0.06
     انتقال
    -0.06
     Milano
    -0.06
    POSITIVE LOGITS
     resulting
    0.07
    .enums
    0.06
    قط
    0.06
    _defs
    0.06
    !(:
    0.06
    sqrt
    0.06
    思想
    0.06
     الأن
    0.06
    991
    0.06
    ’ı
    0.06
    Act Density 0.005%

    No Known Activations