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

    Neuronpedia

    INDEX
    Explanations

    sections that contain numerical data or statistics

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

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.42
     оригіналу
    -0.39
    ofan
    -0.37
    stle
    -0.36
     Sorg
    -0.36
     cashier
    -0.35
    lede
    -0.34
     مرئيه
    -0.34
    Tikang
    -0.34
    seud
    -0.33
    POSITIVE LOGITS
     Савезне
    0.57
     Comprometido
    0.56
    webElementXpaths
    0.52
    دانشنامهٔ
    0.51
     geloof
    0.48
    Хьажоргаш
    0.47
     disambiguazione
    0.47
    CloseOperation
    0.47
     męski
    0.47
     autorité
    0.47
    Act Density 0.355%

    No Known Activations