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

    Neuronpedia

    INDEX
    Explanations

    references to a "model" in various contexts

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

    user model

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects occurrences of the word "model" (the token "model").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.60
     Мексичка
    -0.59
    ftagPool
    -0.54
     wireType
    -0.50
     mergeFrom
    -0.50
    Manbalar
    -0.49
     صوتيه
    -0.49
     surla
    -0.49
    MessageTagHelper
    -0.48
    RegressionTest
    -0.47
    POSITIVE LOGITS
    model
    1.46
     model
    1.10
    Model
    1.06
    MODEL
    1.03
     Model
    1.01
     MODEL
    0.98
    models
    0.91
    modell
    0.88
    モデル
    0.87
    modelo
    0.84
    Act Density 0.000%

    No Known Activations