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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and their contributions

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

    academic publication abstract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.59
    IsContent
    -0.57
    tagHelper
    -0.54
    SourceChecksum
    -0.54
    stylers
    -0.54
    脚注の使い方
    -0.53
     ProtoMessage
    -0.53
     Púb
    -0.53
    adaptiveStyles
    -0.51
    setof
    -0.50
    POSITIVE LOGITS
     surla
    0.49
    Попис
    0.42
    kuuta
    0.41
     Wirtschafts
    0.39
    Tracce
    0.35
     mema
    0.34
    guien
    0.32
    providedIn
    0.32
    ąc
    0.31
     gre
    0.31
    Act Density 0.121%

    No Known Activations