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

    Neuronpedia

    INDEX
    Explanations

    say the ending -ings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cheeses
    -0.07
    paration
    -0.06
     gray
    -0.06
    .sun
    -0.06
     inicio
    -0.06
     secret
    -0.06
     document
    -0.06
     Rum
    -0.06
    	query
    -0.06
        	↵
    -0.06
    POSITIVE LOGITS
     phẩm
    0.08
    통
    0.07
     peně
    0.07
    ้า
    0.06
    .getStatusCode
    0.06
    빙
    0.06
     охорони
    0.06
    ANDING
    0.06
    _LOADING
    0.06
    $lang
    0.06
    Act Density 0.001%

    No Known Activations