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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Creating
    -0.07
    .perm
    -0.07
     leverage
    -0.06
    ुल
    -0.06
    _C
    -0.06
     Ради
    -0.06
    .getActive
    -0.06
    <Resource
    -0.06
     Claus
    -0.06
    Overlap
    -0.06
    POSITIVE LOGITS
    (uint
    0.07
     منت
    0.07
    (world
    0.06
     dislike
    0.06
    umlah
    0.06
     ){↵↵
    0.06
     manufacturers
    0.06
    unic
    0.06
    inez
    0.06
     bless
    0.06
    Act Density 0.002%

    No Known Activations