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

    Neuronpedia

    INDEX
    Explanations

    court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    关系
    -0.07
     Susan
    -0.06
    ازند
    -0.06
    Dar
    -0.06
    more
    -0.06
    ิดข
    -0.06
     Arithmetic
    -0.06
    ря
    -0.06
    Ｃ
    -0.06
    _st
    -0.06
    POSITIVE LOGITS
     lesbians
    0.07
     respondent
    0.07
     Vill
    0.07
    	Class
    0.06
     isKindOfClass
    0.06
    .rect
    0.06
    ITTLE
    0.06
    .mozilla
    0.06
     hereby
    0.06
    Verified
    0.06
    Act Density 0.003%

    No Known Activations