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

    Neuronpedia

    INDEX
    Explanations

    code output/subprocess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Shift
    -0.08
    ensor
    -0.08
    .shift
    -0.07
     Middleton
    -0.07
     délicieux
    -0.07
     sarcas
    -0.07
    .delete
    -0.07
    editor
    -0.07
    Swipe
    -0.07
    shift
    -0.07
    POSITIVE LOGITS
    φα
    0.08
     symbol
    0.08
     ಸಿನಿಮ
    0.08
    	ff
    0.08
     encontr
    0.08
     Auto
    0.08
     adults
    0.08
    _SYMBOL
    0.08
     gord
    0.07
     సినిమ
    0.07
    Act Density 0.000%

    No Known Activations