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

    Neuronpedia

    INDEX
    Explanations

    semicircles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .transaction
    -0.09
    .global
    -0.08
     err
    -0.08
    .lex
    -0.08
    .document
    -0.08
    дал
    -0.08
    .market
    -0.08
    全球
    -0.07
     précédent
    -0.07
    (global
    -0.07
    POSITIVE LOGITS
    curve
    0.09
     costa
    0.08
     технологии
    0.08
     квадрат
    0.08
    jela
    0.08
     JBL
    0.08
     promen
    0.08
     Hoog
    0.08
     Curve
    0.08
     海南
    0.08
    Act Density 0.035%

    No Known Activations