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

    Neuronpedia

    INDEX
    Explanations

    dash-separated phrases and citations

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    es
    -0.71
    as
    -0.67
    jas
    -0.60
    ens
    -0.57
    mentions
    -0.57
    te
    -0.57
    de
    -0.56
    to
    -0.54
    wsdl
    -0.54
    ES
    -0.53
    POSITIVE LOGITS
    /*
    0.75
    tagext
    0.66
    TagMode
    0.65
     estekak
    0.57
    tagHelperRunner
    0.56
    elfth
    0.55
     <=",
    0.55
     ModelExpression
    0.54
     оригіналу
    0.54
    /**
    0.54
    Act Density 14.071%

    No Known Activations