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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic or formal research discussions

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

    incorporated herein

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    页面存档备份
    -0.35
     createState
    -0.32
    strona
    -0.31
     viajar
    -0.30
    isch
    -0.30
     الحره
    -0.30
    Dokument
    -0.30
     posisi
    -0.30
    nă
    -0.29
    Document
    -0.29
    POSITIVE LOGITS
     censiti
    0.68
     CanadaChoose
    0.63
    webElementXpaths
    0.62
    DockStyle
    0.59
    weightedMode
    0.58
    writeFieldEnd
    0.58
    multicolumn
    0.57
    0.57
    ScopeManager
    0.56
    riwal
    0.56
    Act Density 0.410%

    No Known Activations