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

    Neuronpedia

    INDEX
    Explanations

    the word "Instance" and words/phrases associated with options/defaults

    oai_token-act-pair · gemini-2.0-flash

    instance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.70
     Don
    -0.56
     the
    -0.54
    "
    -0.53
    '
    -0.49
    Don
    -0.49
    autor
    -0.49
     input
    -0.49
     mesures
    -0.48
    casm
    -0.47
    POSITIVE LOGITS
     MainAxisSize
    1.41
     المعيارى
    1.30
    RenderAtEndOf
    1.26
    tvguidetime
    1.20
    ValueStyle
    1.09
     مشين
    1.09
     unknownFields
    1.07
    RectangleBorder
    1.07
     فريبيس
    1.04
    mybatisplus
    1.04
    Act Density 0.451%

    No Known Activations