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

    Neuronpedia

    INDEX
    Explanations

    accuracy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bef
    -0.07
    試
    -0.07
    entre
    -0.07
    ynam
    -0.07
     nav
    -0.07
     Univers
    -0.06
    　V
    -0.06
    пов
    -0.06
    RegExp
    -0.06
     본
    -0.06
    POSITIVE LOGITS
    .website
    0.07
    .GREEN
    0.06
     charm
    0.06
    。而
    0.06
     toJSON
    0.06
    _STOCK
    0.06
    .Stderr
    0.06
     legalize
    0.06
    _TRIANGLES
    0.06
    sgiving
    0.05
    Act Density 0.012%

    No Known Activations