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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and symbols in contextual discussions

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

    non-english language content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.40
    RegressionTest
    -0.34
    slf
    -0.34
    Искәрмәләр
    -0.32
     encomp
    -0.32
    Referințe
    -0.32
    ut
    -0.31
    แรง
    -0.31
     Univers
    -0.30
     levan
    -0.30
    POSITIVE LOGITS
     resourceCulture
    0.57
    enterOuterAlt
    0.56
    ⟬
    0.52
    KommentareTeilen
    0.51
    matchCondition
    0.51
    Чтоб
    0.48
    RenderAtEndOf
    0.48
    脚注の使い方
    0.48
    extAlignment
    0.48
    AutoScaleMode
    0.47
    Act Density 0.358%

    No Known Activations