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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code and code snippets

    oai_token-act-pair · gemini-2.0-flash

    Brackets/code/math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.66
     '\\;'
    -0.89
    Vidite
    -0.87
     kaarangay
    -0.83
    BeginContext
    -0.78
    #
    -0.78
     المعيارى
    -0.75
     AspNetCore
    -0.72
    Erreferentziak
    -0.72
     Winaray
    -0.71
    POSITIVE LOGITS
    amili
    0.50
     exceptions
    0.47
     exception
    0.47
     Exceptions
    0.45
     타
    0.42
    vil
    0.42
    ($__
    0.41
    ukai
    0.41
    yl
    0.41
    arti
    0.41
    Act Density 1.545%

    No Known Activations