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

    Neuronpedia

    INDEX
    Explanations

    modular arithmetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Schönheit
    -0.08
    玲
    -0.08
     philosophical
    -0.08
     appeals
    -0.08
    Linecap
    -0.08
     Aman
    -0.08
     تحفظ
    -0.07
    Overwrite
    -0.07
     omo
    -0.07
     muuq
    -0.07
    POSITIVE LOGITS
     ਵਰ
    0.07
     golden
    0.07
    ោះ
    0.07
     Golden
    0.07
     Shooter
    0.07
     Tests
    0.07
     healthiest
    0.07
    Chosen
    0.07
    _IRQn
    0.07
     enabled
    0.07
    Act Density 0.013%

    No Known Activations