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
     conceptual
    -0.07
     suppression
    -0.07
     Kemp
    -0.06
    mit
    -0.06
    ainers
    -0.06
    begin
    -0.06
     melt
    -0.06
    kip
    -0.06
    'im
    -0.06
     briefly
    -0.06
    POSITIVE LOGITS
    Authority
    0.07
     suitability
    0.07
     olmuş
    0.07
     UITapGestureRecognizer
    0.07
    _tok
    0.06
     примерно
    0.06
    ROC
    0.06
    .nasa
    0.06
     seaborn
    0.06
     başladı
    0.06
    Act Density 0.002%

    No Known Activations