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

    Neuronpedia

    INDEX
    Explanations

    Chicago

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lowercase
    -0.08
     LANGUAGE
    -0.07
     XII
    -0.07
     endDate
    -0.07
    uropean
    -0.07
     Born
    -0.06
     Phase
    -0.06
    (gs
    -0.06
     Throwable
    -0.06
     opendir
    -0.06
    POSITIVE LOGITS
     Seattle
    0.08
     Detroit
    0.07
     Classe
    0.06
     Atlanta
    0.06
     평
    0.06
     servings
    0.06
     ترك
    0.06
    nesota
    0.06
     dla
    0.06
     Milwaukee
    0.06
    Act Density 0.047%

    No Known Activations