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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GES
    -0.07
    errat
    -0.07
    consistent
    -0.07
     males
    -0.06
     compromising
    -0.06
     abrupt
    -0.06
     ориг
    -0.06
    期間
    -0.06
    endDate
    -0.06
     його
    -0.06
    POSITIVE LOGITS
     productService
    0.07
     bash
    0.06
     Topics
    0.06
     //!<
    0.06
    _navigation
    0.06
    	puts
    0.06
     〉
    0.06
     oppression
    0.06
    -oper
    0.06
    。”
    0.06
    Act Density 0.000%

    No Known Activations