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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Charity
    -0.07
     आत
    -0.07
     foreign
    -0.07
    urret
    -0.07
    选择
    -0.06
    ({});↵
    -0.06
    Estado
    -0.06
    dataset
    -0.06
    <U
    -0.06
    Laura
    -0.06
    POSITIVE LOGITS
     Gord
    0.07
     sonra
    0.06
    .tem
    0.06
     Investing
    0.06
     overlook
    0.06
     ülk
    0.06
    澤
    0.06
     —
    0.06
    .testing
    0.06
    ACK
    0.06
    Act Density 0.001%

    No Known Activations