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

    Neuronpedia

    INDEX
    Explanations

    Json

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purpose
    -0.07
    	driver
    -0.07
     deaths
    -0.07
    ektör
    -0.07
    -sidebar
    -0.07
    死
    -0.06
     jouer
    -0.06
    money
    -0.06
    姐
    -0.06
     přek
    -0.06
    POSITIVE LOGITS
    :animated
    0.07
     Discord
    0.06
    imos
    0.06
    Connections
    0.06
     ﾊ
    0.06
    ::↵↵
    0.06
    (Stream
    0.06
    ,no
    0.06
    .TextUtils
    0.06
    igest
    0.06
    Act Density 0.010%

    No Known Activations