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

    Neuronpedia

    INDEX
    Explanations

    Enterprise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     集
    -0.08
    (album
    -0.07
    姉
    -0.07
    _np
    -0.06
     Wants
    -0.06
     dB
    -0.06
    oters
    -0.06
    -Al
    -0.06
    mj
    -0.06
    曜日
    -0.06
    POSITIVE LOGITS
     breach
    0.08
    ροφορ
    0.07
     cle
    0.07
    voor
    0.06
    ovatel
    0.06
    .ManyToManyField
    0.06
     Cookies
    0.06
     Пом
    0.06
    ΟΜ
    0.06
    egasus
    0.06
    Act Density 0.003%

    No Known Activations