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

    Neuronpedia

    INDEX
    Explanations

    external sources or quotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Justin
    -0.07
     delighted
    -0.07
     août
    -0.06
     męż
    -0.06
     disaster
    -0.06
     userdata
    -0.06
    勇士
    -0.06
    薪
    -0.06
     weekly
    -0.06
    ชนะ
    -0.06
    POSITIVE LOGITS
     CRT
    0.07
    (TokenType
    0.07
    CRT
    0.07
     ViewState
    0.07
    的味道
    0.07
    畤
    0.07
     komm
    0.06
    �
    0.06
    论
    0.06
    帶
    0.06
    Act Density 0.091%

    No Known Activations