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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incorrect
    -0.07
    DP
    -0.07
    _face
    -0.07
     Lindsey
    -0.06
    echo
    -0.06
    azel
    -0.06
    	echo
    -0.06
    UIAlert
    -0.06
     salads
    -0.06
     Feedback
    -0.06
    POSITIVE LOGITS
     trois
    0.07
    >All
    0.07
    κρι
    0.07
    γού
    0.06
    IVER
    0.06
    		
↵
↵
    0.06
    .clientHeight
    0.06
    џџџ
    0.06
    =[[
    0.06
     пов
    0.06
    Act Density 0.065%

    No Known Activations