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

    Neuronpedia

    INDEX
    Explanations

    code structure and syntax elements in programming

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

    `set` methods or properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.90
    parsedMessage
    -0.85
    LookAnd
    -0.83
    脚注の使い方
    -0.83
     '\\;'
    -0.76
    Autoritní
    -0.73
    ----</
    -0.72
    Rüyada
    -0.71
    RectangleBorder
    -0.71
     صوتيه
    -0.71
    POSITIVE LOGITS
     trenes
    0.30
     sitten
    0.28
     bendera
    0.28
     nostru
    0.28
     calabaza
    0.28
     Thiết
    0.27
     Noviembre
    0.27
     treno
    0.27
     diritto
    0.26
     적
    0.26
    Act Density 0.005%

    No Known Activations