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

    Neuronpedia

    INDEX
    Explanations

    constructs and syntax elements relevant to programming or scripting languages

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

    programming code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.44
     financiación
    -0.42
     oídos
    -0.40
     graças
    -0.40
     expuesto
    -0.39
    راث
    -0.39
     Einfluss
    -0.39
     cortesía
    -0.39
    Atentamente
    -0.39
     comiendo
    -0.38
    POSITIVE LOGITS
    CreateModel
    1.47
    modelBuilder
    0.61
     surla
    0.56
    IContainer
    0.56
     NgModule
    0.54
     autorytatywna
    0.52
    createElement
    0.49
    llary
    0.49
    UserScript
    0.49
     Model
    0.48
    Act Density 0.000%

    No Known Activations