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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     số
    -0.08
     crafted
    -0.07
    𝓸
    -0.07
    ignore
    -0.07
    aybe
    -0.07
     wys
    -0.07
    [event
    -0.06
    特殊的
    -0.06
    ecal
    -0.06
     Devin
    -0.06
    POSITIVE LOGITS
    ))]
    0.08
    数据中心
    0.08
    ')),
    0.07
    格會員
    0.07
     meaning
    0.07
    "]);↵
    0.07
     السنة
    0.07
    ())),
    0.07
    ']=
    0.07
    reach
    0.07
    Act Density 0.005%

    No Known Activations