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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and expressions

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

    mathematical variables and code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujung
    -0.37
     olvidado
    -0.36
    เข
    -0.36
     klaar
    -0.35
     ulang
    -0.35
     geïsole
    -0.35
    UrlResolution
    -0.35
     extré
    -0.34
     atendido
    -0.33
     supérieures
    -0.33
    POSITIVE LOGITS
    sizeCache
    0.64
     OFDb
    0.63
     pinulongan
    0.61
     surla
    0.59
     ویکی‌پدی
    0.57
    hoeddwyd
    0.54
    Tembelea
    0.53
    istoitu
    0.53
    曖昧さ回避
    0.51
    complexContent
    0.50
    Act Density 0.231%

    No Known Activations