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

    Neuronpedia

    INDEX
    Explanations

    Regression models

    np_max-act · gemini-2.0-flash

    definitions and explanations related to neural language models.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron lightly activates on technical terms describing model operations or components—words like “enc(oder),” “predicting,” or “sequence.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    adeon
    -0.08
    .$$
    -0.07
    (goal
    -0.06
    kemiz
    -0.06
    opencv
    -0.06
    集中
    -0.06
    Device
    -0.06
     روسی
    -0.06
    La
    -0.06
     conform
    -0.06
    POSITIVE LOGITS
    -age
    0.06
    َال
    0.06
    リーズ
    0.06
    仁
    0.06
    ามารถ
    0.06
    援
    0.06
     wear
    0.06
     strengthened
    0.06
    irq
    0.06
    瑞
    0.06
    Act Density 0.013%

    No Known Activations