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

    Neuronpedia

    INDEX
    Explanations

    Python import statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    谨慎
    -0.08
    领导下
    -0.08
    几种
    -0.08
    のみ
    -0.07
     disqualified
    -0.07
    -0.07
    allest
    -0.07
    很多
    -0.07
     Allocation
    -0.07
     lég
    -0.06
    POSITIVE LOGITS
     בחו
    0.08
     QtWidgets
    0.07
     кач
    0.07
    囡
    0.07
    zes
    0.07
    pora
    0.07
     nhật
    0.06
    蓦
    0.06
     mockery
    0.06
    `}↵
    0.06
    Act Density 0.015%

    No Known Activations