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
     rpc
    -0.07
    !=(
    -0.06
    ibar
    -0.06
    Bookmark
    -0.06
    other
    -0.06
    would
    -0.06
    igsaw
    -0.06
    crast
    -0.06
    Demo
    -0.06
    ою
    -0.06
    POSITIVE LOGITS
     professor
    0.06
    .Res
    0.06
     Bos
    0.06
    .turn
    0.06
     Description
    0.06
     femme
    0.06
     parameter
    0.06
     sugars
    0.06
    骑
    0.06
     convention
    0.06
    Act Density 0.018%

    No Known Activations