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

    Neuronpedia

    INDEX
    Explanations

    Period punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    528
    -0.07
    fn
    -0.07
    GGLE
    -0.07
    (cond
    -0.07
    suffix
    -0.06
    puts
    -0.06
    Floating
    -0.06
    leaders
    -0.06
    _exclude
    -0.06
    мир
    -0.06
    POSITIVE LOGITS
    )}↵
    0.07
    اعت
    0.07
    `)↵
    0.06
    ونت
    0.06
    ").↵
    0.06
    gesch
    0.06
    '}),↵
    0.06
    /↵↵↵↵
    0.06
     Motorcycle
    0.06
     nek
    0.06
    Act Density 0.054%

    No Known Activations