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

    Neuronpedia

    INDEX
    Explanations

    —but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,"%
    -0.07
     ди
    -0.07
     врач
    -0.06
    orraine
    -0.06
     fern
    -0.06
    阵
    -0.06
    endum
    -0.06
     concerted
    -0.06
     Er
    -0.06
    gar
    -0.06
    POSITIVE LOGITS
    Listing
    0.06
     sanity
    0.06
     giả
    0.06
    Controllers
    0.06
    $args
    0.06
    pressive
    0.06
    .Column
    0.06
    OrFail
    0.06
     veg
    0.06
    .Sqrt
    0.06
    Act Density 0.186%

    No Known Activations