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

    Neuronpedia

    INDEX
    Explanations

    book descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    วร
    -0.07
     disagreements
    -0.06
     impecc
    -0.06
     mez
    -0.06
     Sax
    -0.06
    ugin
    -0.06
    Maps
    -0.06
    Bur
    -0.06
    (/[
    -0.06
    _impl
    -0.06
    POSITIVE LOGITS
    (photo
    0.07
     "
↵
    0.06
    .xls
    0.06
    .metric
    0.06
     déjà
    0.06
    лось
    0.06
     Dummy
    0.06
     stagger
    0.06
    україн
    0.06
    802
    0.06
    Act Density 0.064%

    No Known Activations