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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,
    -0.87
    d
    -0.60
    p
    -0.58
    m
    -0.54
    -
    -0.54
     and
    -0.52
    ms
    -0.51
    b
    -0.51
    in
    -0.50
    s
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.94
    Autoritní
    0.88
    <bos>
    0.85
     autorytatywna
    0.82
    uxxxx
    0.82
    Gambas
    0.82
    webElement
    0.79
     Italijanski
    0.79
    Manbalar
    0.78
    iſten
    0.78
    Act Density 0.097%

    No Known Activations