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

    Neuronpedia

    INDEX
    Explanations

    negative exponents

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.92
    AddTagHelper
    -0.77
    UserScript
    -0.75
    PerformLayout
    -0.71
     Latte
    -0.69
     Mohr
    -0.69
    sonian
    -0.68
     fieldNum
    -0.68
     OAS
    -0.67
     تضيفلها
    -0.66
    POSITIVE LOGITS
    ğından
    0.63
     Braunschweig
    0.59
    Ligações
    0.55
    FROM
    0.55
     Beaufort
    0.54
    참고
    0.52
     writeTo
    0.51
    databind
    0.50
    unsqueeze
    0.50
    őle
    0.50
    Act Density 0.010%

    No Known Activations