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

    Neuronpedia

    INDEX
    Explanations

    code and code-related language (e.g. comments or documentation)

    oai_token-act-pair · gemini-2.0-flash

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ar
    -0.94
    al
    -0.94
    _
    -0.92
    f
    -0.91
    l
    -0.89
    na
    -0.89
    3
    -0.88
    c
    -0.87
    r
    -0.86
    n
    -0.85
    POSITIVE LOGITS
    SourceChecksum
    1.36
    IUrlHelper
    1.33
     Мексичка
    1.26
    ousands
    1.20
    hematical
    1.19
    NUMX
    1.18
    esterday
    1.16
    ^(@)
    1.14
    iffance
    1.13
    olesale
    1.12
    Act Density 2.172%

    No Known Activations