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

    Neuronpedia

    INDEX
    Explanations

    references to JavaScript code and operations related to data fetching and manipulation

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

    user input start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wireType
    -0.68
    ArrowToggle
    -0.60
     ainfi
    -0.56
    SharedDtor
    -0.56
    rrggbb
    -0.56
     avoient
    -0.54
    charpe
    -0.54
     mauva
    -0.54
    TAWA
    -0.52
    zijn
    -0.50
    POSITIVE LOGITS
    antd
    0.79
     Ges
    0.35
     Kla
    0.35
     pen
    0.35
     cit
    0.34
    pNode
    0.34
    leg
    0.33
     nom
    0.33
     kont
    0.33
     Kwa
    0.33
    Act Density 0.003%

    No Known Activations