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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific publications or journals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    specific journal titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.37
    setFill
    -0.36
     Wayback
    -0.34
     Wellen
    -0.34
    getDeclared
    -0.33
    pyplot
    -0.33
     pungkas
    -0.33
    íferos
    -0.33
     familiar
    -0.32
    Litteratur
    -0.32
    POSITIVE LOGITS
     CreateTagHelper
    0.77
    tagHelperRunner
    0.72
    ValueStyle
    0.66
     ***!
    0.65
    principalColumn
    0.64
    下载附件
    0.63
    ViewFeatures
    0.61
     kaarangay
    0.61
    uxxxx
    0.60
     noqa
    0.59
    Act Density 0.786%

    No Known Activations