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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Mapping
    -0.07
    (format
    -0.07
    ;%
    -0.07
    omedical
    -0.07
     français
    -0.07
    ulist
    -0.07
    去年
    -0.07
     systemFontOfSize
    -0.06
     novembre
    -0.06
    mmc
    -0.06
    POSITIVE LOGITS
    UU
    0.07
     ס
    0.07
    ジャ
    0.07
     בס
    0.06
    vals
    0.06
     stores
    0.06
     broadcasts
    0.06
    公益活动
    0.06
    橡胶
    0.06
    _MSG
    0.06
    Act Density 0.253%

    No Known Activations