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

    Neuronpedia

    INDEX
    Explanations

    problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nu
    -0.07
     ensl
    -0.07
    empo
    -0.06
    	U
    -0.06
    .Foundation
    -0.06
     кіль
    -0.06
    Dan
    -0.06
    usive
    -0.06
    (Schedulers
    -0.06
    Vict
    -0.06
    POSITIVE LOGITS
     ListView
    0.07
    ์ฟ
    0.07
    =model
    0.07
     Detroit
    0.07
    (angle
    0.07
    :frame
    0.07
    距离
    0.06
     socket
    0.06
    (Blueprint
    0.06
     منزل
    0.06
    Act Density 0.037%

    No Known Activations