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

    Neuronpedia

    INDEX
    Explanations

    references to data models and their structures

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

    `ListModel` and `model`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?>">
    -0.33
    ToReturn
    -0.33
    ToServer
    -0.31
    若
    -0.31
     fér
    -0.30
    зовы
    -0.29
    Itoa
    -0.29
     הת
    -0.29
    newVal
    -0.29
    Tác
    -0.28
    POSITIVE LOGITS
     model
    2.94
    model
    2.73
     Model
    2.67
    Model
    2.63
     MODEL
    2.50
    MODEL
    2.30
     modelo
    2.25
     models
    2.23
     modèle
    2.22
    モデル
    2.22
    Act Density 0.011%

    No Known Activations