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

    Neuronpedia

    INDEX
    Explanations

    constructor methods in programming code, specifically indicating the presence of object initialization functions

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

    __init__ self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.00
     propOrder
    -0.96
    Tikang
    -0.85
    verwijspagina
    -0.84
    IsMutable
    -0.81
     daysTop
    -0.81
     ModelExpression
    -0.80
     パンチラ
    -0.80
    <unused22>
    -0.79
    tanleria
    -0.79
    POSITIVE LOGITS
    __(
    0.59
    (
    0.39
    The
    0.34
     (
    0.34
    page
    0.32
    main
    0.31
    ...
    0.31
    paper
    0.30
     __(
    0.30
    La
    0.29
    Act Density 0.002%

    No Known Activations