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

    Neuronpedia

    INDEX
    Explanations

    references to model definitions in programming or software contexts

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

    model loading or defining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     engraçadas
    -0.44
     aDecoder
    -0.42
    FileInputStream
    -0.41
     jagung
    -0.40
     desperdic
    -0.40
     distinction
    -0.39
     Distinguished
    -0.39
     distinción
    -0.39
    minecraftforge
    -0.39
    一口气
    -0.39
    POSITIVE LOGITS
    model
    2.14
    Model
    1.18
    MODEL
    1.17
     Model
    1.05
     model
    1.04
     MODEL
    1.02
    models
    0.95
    modell
    0.90
    setModel
    0.90
     getModel
    0.90
    Act Density 0.004%

    No Known Activations