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

    Neuronpedia

    INDEX
    Explanations

    mocked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    call
    -0.07
    援
    -0.07
    Ele
    -0.07
    좐
    -0.07
     breathe
    -0.07
    xAA
    -0.07
    -thumbnail
    -0.06
    	z
    -0.06
     Gazette
    -0.06
     <<<
    -0.06
    POSITIVE LOGITS
    뷔
    0.07
    icensing
    0.07
    永久
    0.07
     PROVID
    0.07
    的标准
    0.07
    惘
    0.07
    	local
    0.07
    .coroutines
    0.06
    欢乐
    0.06
     đạt
    0.06
    Act Density 0.164%

    No Known Activations