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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dělení
    -0.06
    ResponseStatus
    -0.06
    passport
    -0.06
     Wants
    -0.06
     Suk
    -0.06
     Fans
    -0.06
    earchBar
    -0.06
    <Link
    -0.06
     Depart
    -0.06
    classnames
    -0.06
    POSITIVE LOGITS
     lions
    0.07
     bree
    0.06
     shortcode
    0.06
    ственной
    0.06
     candy
    0.06
     diluted
    0.06
     कभ
    0.06
    mmo
    0.06
    кому
    0.06
     붙
    0.06
    Act Density 0.029%

    No Known Activations