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
    ')}}">
    -0.07
     mejores
    -0.06
    _animation
    -0.06
     Jew
    -0.06
     μία
    -0.06
     кож
    -0.06
     ου
    -0.06
     를
    -0.06
    _after
    -0.06
    -West
    -0.06
    POSITIVE LOGITS
    underscore
    0.07
     yine
    0.06
    quares
    0.06
    .Section
    0.06
    igor
    0.06
     squares
    0.06
    ór
    0.06
    ngen
    0.06
    ケット
    0.06
     irrit
    0.06
    Act Density 0.010%

    No Known Activations