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

    Neuronpedia

    INDEX
    Explanations

    reports ratings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    谢
    -0.07
     metal
    -0.07
    =time
    -0.06
     suspense
    -0.06
    _write
    -0.06
     cor
    -0.06
     governmental
    -0.06
     worlds
    -0.06
    参数
    -0.06
    igits
    -0.06
    POSITIVE LOGITS
    DECREF
    0.06
    ,),↵
    0.06
     Ú
    0.06
     éc
    0.06
     BAR
    0.06
    最大
    0.06
    ูปแบบ
    0.06
     kelim
    0.06
     discard
    0.06
    HasColumnType
    0.06
    Act Density 0.027%

    No Known Activations