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

    Neuronpedia

    INDEX
    Explanations

    code/data/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rp
    -0.07
    _HELPER
    -0.07
    儀
    -0.07
    .urls
    -0.07
    刻
    -0.06
    xes
    -0.06
    ّم
    -0.06
    Gap
    -0.06
     �
    -0.06
    _estimator
    -0.06
    POSITIVE LOGITS
    0.07
     SAS
    0.07
     bırak
    0.06
     Stanton
    0.06
    ulla
    0.06
     Pittsburgh
    0.06
     UNESCO
    0.06
     dưới
    0.06
    阳城
    0.06
    ')"↵
    0.06
    Act Density 0.004%

    No Known Activations