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

    Neuronpedia

    INDEX
    Explanations

    indicators of timed events or processes

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

    Text appearing before section headers or introductions

    np_acts-logits-general · gemini-2.0-flash

    troubleshooting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.71
    parsedMessage
    -0.68
    Geplaatst
    -0.68
    -0.68
     propOrder
    -0.65
    ValueStyle
    -0.58
     Majefty
    -0.56
    !")
    -0.56
     jScrollPane
    -0.56
    attendre
    -0.55
    POSITIVE LOGITS
     when
    0.66
     amikor
    0.64
    when
    0.63
    的时候
    0.59
     cuando
    0.57
    geren
    0.56
     berikutnya
    0.56
    лактика
    0.56
     quando
    0.56
    uct
    0.55
    Act Density 0.401%

    No Known Activations