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
     لديك
    -0.09
    segue
    -0.08
    ել
    -0.08
     curricula
    -0.08
    _properties
    -0.08
    agenda
    -0.08
    bibli
    -0.08
    ("""↵
    -0.08
    Utils
    -0.08
     обнаруж
    -0.07
    POSITIVE LOGITS
     parentheses
    0.14
     commas
    0.12
     brackets
    0.10
     parentes
    0.10
     braces
    0.10
     quotation
    0.09
     vowels
    0.09
     curly
    0.09
     whites
    0.09
     '='
    0.08
    Act Density 0.059%

    No Known Activations