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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    小孩子
    -0.08
     helmets
    -0.07
     MIME
    -0.07
    _EVAL
    -0.07
     trữ
    -0.06
    亥
    -0.06
     BITS
    -0.06
    龠
    -0.06
    要么
    -0.06
     mutually
    -0.06
    POSITIVE LOGITS
    建議
    0.07
     weight
    0.07
    過程
    0.07
    {},↵
    0.07
    続く
    0.07
    roduced
    0.07
    om
    0.07
    ия
    0.07
    Genre
    0.06
     study
    0.06
    Act Density 0.026%

    No Known Activations