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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _qty
    -0.07
    方
    -0.07
     vault
    -0.07
     maison
    -0.07
     vyrá
    -0.06
     grids
    -0.06
     교수
    -0.06
     소개
    -0.06
    _ul
    -0.06
    _pw
    -0.06
    POSITIVE LOGITS
    끔
    0.07
    رس
    0.06
    :UIButtonTypeCustom
    0.06
     Perl
    0.06
    .Tensor
    0.06
     міся
    0.05
    érica
    0.05
    лей
    0.05
    onis
    0.05
    ,M
    0.05
    Act Density 0.005%

    No Known Activations