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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Semantic
    -0.08
     pdf
    -0.07
    .square
    -0.07
     avi
    -0.07
    (web
    -0.06
     preds
    -0.06
     camps
    -0.06
    ,total
    -0.06
    市
    -0.06
     Sacred
    -0.06
    POSITIVE LOGITS
    اخ
    0.07
    HG
    0.07
    ordin
    0.06
    аніт
    0.06
    argon
    0.06
     outer
    0.06
     alloc
    0.06
    ///↵
    0.06
    asını
    0.06
    рова
    0.06
    Act Density 0.001%

    No Known Activations