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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and data structures

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

    technical and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NPD
    -0.39
    only
    -0.38
    iser
    -0.37
    veloper
    -0.36
    bar
    -0.35
    oter
    -0.35
    hile
    -0.35
    PA
    -0.34
     Deco
    -0.34
    RegistryLite
    -0.34
    POSITIVE LOGITS
    IUrlHelper
    0.58
    әрмәләр
    0.57
     disambiguazione
    0.54
     avoient
    0.46
     adequado
    0.46
     surla
    0.46
    Goodnight
    0.46
     validamos
    0.44
     saites
    0.44
     ब्रेकडाउन
    0.43
    Act Density 0.007%

    No Known Activations