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

    Neuronpedia

    INDEX
    Explanations

    code/scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ection
    -0.06
     بنی
    -0.06
     varargin
    -0.06
    ुद
    -0.06
    ασ
    -0.06
     Нас
    -0.06
    _friend
    -0.06
    _lowercase
    -0.06
    .Multiline
    -0.06
    anding
    -0.06
    POSITIVE LOGITS
     dt
    0.06
    ئت
    0.06
     départ
    0.06
     flavors
    0.06
    X
    0.06
    .function
    0.06
     resend
    0.06
     Tue
    0.06
     bab
    0.06
    웅
    0.06
    Act Density 0.000%

    No Known Activations