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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    낳
    -0.07
     Atmos
    -0.07
    servers
    -0.07
    NotExist
    -0.07
    凰
    -0.07
     başlat
    -0.07
    ☵
    -0.07
    مف
    -0.07
     getContentPane
    -0.07
     Police
    -0.06
    POSITIVE LOGITS
    eryl
    0.08
    ồ
    0.07
    Б
    0.07
     Series
    0.06
    陈
    0.06
     Arthur
    0.06
    .checked
    0.06
    _'.$
    0.06
    ],[-
    0.06
    数组
    0.06
    Act Density 0.003%

    No Known Activations