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

    Neuronpedia

    INDEX
    Explanations

    something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    upd
    -0.08
    在網路上
    -0.07
    zl
    -0.07
    dıktan
    -0.07
     stew
    -0.06
    (mysql
    -0.06
    独一
    -0.06
    벋
    -0.06
     aDecoder
    -0.06
    yü
    -0.06
    POSITIVE LOGITS
    般的
    0.08
     Amount
    0.07
    田园
    0.07
     Urban
    0.07
    ками
    0.07
    quent
    0.07
    시스
    0.07
    olecule
    0.07
     )↵
    0.07
     GREAT
    0.07
    Act Density 0.020%

    No Known Activations