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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ניוז
    -0.08
    utsche
    -0.08
    chluss
    -0.08
    副院长
    -0.07
    띕
    -0.07
    ус
    -0.07
    otron
    -0.07
    勖
    -0.06
     điển
    -0.06
    /cmd
    -0.06
    POSITIVE LOGITS
     obra
    0.07
    ocre
    0.07
    Tables
    0.07
    澳门
    0.07
     COLORS
    0.07
    Número
    0.07
    (ro
    0.07
    _total
    0.06
    .POS
    0.06
    Hor
    0.06
    Act Density 0.065%

    No Known Activations