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

    Neuronpedia

    INDEX
    Explanations

    elements related to neural network architectures and their configurations

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

    resolution loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parezca
    -0.32
    colgante
    -0.32
     nación
    -0.31
     jeter
    -0.31
     normes
    -0.31
    irsi
    -0.30
     Construcción
    -0.29
    ene
    -0.29
     kambing
    -0.29
    links
    -0.29
    POSITIVE LOGITS
    SharedCtor
    0.62
    Aholisi
    0.60
    0.59
    writeFieldEnd
    0.58
     onPostExecute
    0.56
    webElementXpaths
    0.56
    parsedMessage
    0.56
     Exactos
    0.52
    AnchorStyles
    0.51
    AutoresizingMask
    0.51
    Act Density 0.020%

    No Known Activations