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

    Neuronpedia

    INDEX
    Explanations

    colons enclosed in brackets

    oai_token-act-pair · gemini-2.0-flash

    :]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.14
    :]
    -1.09
     '\\;'
    -0.72
    ThroughAttribute
    -0.70
    :],
    -0.70
    AddTagHelper
    -0.68
     समीक्षक
    -0.67
    AndEndTag
    -0.65
    :])
    -0.65
    Jeografia
    -0.63
    POSITIVE LOGITS
    enares
    0.60
    abbaye
    0.56
     médié
    0.54
     âgées
    0.54
     pram
    0.54
     sauvages
    0.52
    lenmiş
    0.52
    Czytaj
    0.52
     miso
    0.52
     químicas
    0.52
    Act Density 0.103%

    No Known Activations