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

    Neuronpedia

    INDEX
    Explanations

    elements related to data structures and their attributes in programming or documentation

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

    providing descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onPostExecute
    -0.61
    -0.59
     onResponse
    -0.59
    skjaer
    -0.58
    MLLoader
    -0.58
     &___
    -0.57
    utilisons
    -0.56
     DbSet
    -0.54
    apimachinery
    -0.54
    Jîn
    -0.54
    POSITIVE LOGITS
     description
    0.54
     descripción
    0.49
     descrizione
    0.47
     descrição
    0.44
     describir
    0.44
     descriptions
    0.42
     décrire
    0.42
     explains
    0.42
     explanation
    0.42
     explicación
    0.42
    Act Density 0.179%

    No Known Activations