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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    いて
    -0.07
    铁
    -0.07
    _BOARD
    -0.07
     handicap
    -0.07
    olls
    -0.07
    礓
    -0.07
     immac
    -0.07
    oint
    -0.06
    ₲
    -0.06
    جون
    -0.06
    POSITIVE LOGITS
    ustomer
    0.07
     Remed
    0.07
    职位
    0.07
    절차
    0.06
    ítica
    0.06
     job
    0.06
    另一边
    0.06
     nargin
    0.06
    extern
    0.06
    腾讯
    0.06
    Act Density 0.291%

    No Known Activations