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

    Neuronpedia

    INDEX
    Explanations

    names of characters and titles associated with popular media

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

    sci-fi references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indu
    -0.36
    senz
    -0.35
     стой
    -0.34
    StartTag
    -0.30
    [][]
    -0.28
    opheles
    -0.28
    fontName
    -0.28
     Ibis
    -0.28
     Binnen
    -0.27
     intran
    -0.27
    POSITIVE LOGITS
    SourceChecksum
    0.63
    MessageTagHelper
    0.61
     שוליים
    0.59
    Билгалдахарш
    0.57
    InsertCommand
    0.56
     onData
    0.54
     חיצוניים
    0.53
    ionales
    0.53
    errHandler
    0.52
    breng
    0.52
    Act Density 0.004%

    No Known Activations