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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    physical
    -0.07
    でしょう
    -0.06
    걸
    -0.06
     zijn
    -0.06
    ouchers
    -0.06
    靠
    -0.06
     Immigration
    -0.06
    のように
    -0.06
    crime
    -0.06
     유
    -0.06
    POSITIVE LOGITS
    getStatusCode
    0.07
    (parameter
    0.06
    Resume
    0.06
    ök
    0.06
     mixes
    0.06
    .choice
    0.06
    (marker
    0.06
    ади
    0.06
    *K
    0.06
    off
    0.06
    Act Density 0.002%

    No Known Activations