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

    Neuronpedia

    INDEX
    Explanations

    technical terms and variables related to scientific methodologies and studies

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

    technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hasn
    -0.38
     nationaux
    -0.37
     dedans
    -0.37
    hasiswa
    -0.36
    paravant
    -0.36
     vaikka
    -0.36
    addVertex
    -0.35
    vų
    -0.35
     frankly
    -0.35
     tbh
    -0.35
    POSITIVE LOGITS
     disambiguazione
    0.65
     تضيفلها
    0.63
    webElementXpaths
    0.57
    yntaxException
    0.57
    WriteTagHelper
    0.53
    verwijspagina
    0.52
    sizeCache
    0.52
    ConstraintMaker
    0.52
    CppMethod
    0.52
     defaultstate
    0.51
    Act Density 7.117%

    No Known Activations