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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     currentPlayer
    -0.07
     �
    -0.07
    olah
    -0.07
    われる
    -0.07
    xd
    -0.07
    packageName
    -0.06
    getDb
    -0.06
    [op
    -0.06
    ómo
    -0.06
     Bing
    -0.06
    POSITIVE LOGITS
    .charset
    0.07
    실
    0.06
    CHA
    0.06
     lasers
    0.06
    (mysql
    0.06
     CentOS
    0.06
    Factors
    0.06
     чит
    0.06
    MITTED
    0.06
    	angle
    0.06
    Act Density 0.015%

    No Known Activations