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

    Neuronpedia

    INDEX
    Explanations

    keywords related to social structures and identities

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

    Followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    time periods or abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Drapeau
    -0.58
     ModelExpression
    -0.53
    phosa
    -0.51
    tagHelperRunner
    -0.50
    niſſe
    -0.49
     Plug
    -0.45
    extAlignment
    -0.44
    ſehen
    -0.44
     Tür
    -0.43
    EndContext
    -0.43
    POSITIVE LOGITS
    舺
    0.46
    ならではの
    0.45
    ならでは
    0.41
     nahilalakip
    0.40
    parsedMessage
    0.40
     beraber
    0.38
     nakalista
    0.36
    特有
    0.36
    autoreleasepool
    0.36
    蚪
    0.35
    Act Density 0.463%

    No Known Activations