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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cards
    -0.07
     alliance
    -0.07
    [M
    -0.07
     Gloss
    -0.06
    ilis
    -0.06
    Lu
    -0.06
     samt
    -0.06
    /pre
    -0.06
     translating
    -0.06
    ّد
    -0.06
    POSITIVE LOGITS
    (:,
    0.07
     그의
    0.07
     hiçbir
    0.06
     $("<
    0.06
    .DateField
    0.06
    ///////////////////////////////////////////////////////////////////////////////↵
    0.06
     gps
    0.06
    -mort
    0.06
    (tensor
    0.06
    WSC
    0.06
    Act Density 0.130%

    No Known Activations