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

    Neuronpedia

    INDEX
    Explanations

    init

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    axe
    -0.07
     Dane
    -0.07
    .spinner
    -0.07
    莺
    -0.07
    .Exception
    -0.07
     SHARE
    -0.07
    asio
    -0.07
     participating
    -0.07
    Csv
    -0.07
    IRD
    -0.06
    POSITIVE LOGITS
     בלי
    0.08
    等级
    0.07
     °
    0.07
     costo
    0.07
     bur
    0.07
     sürü
    0.07
    훾
    0.06
    Купить
    0.06
    kü
    0.06
    将于
    0.06
    Act Density 0.003%

    No Known Activations