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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash

    contextual code or programming-related elements within a text.

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

    This neuron fires on question components—e.g. interrogative words like “How” and the “?” punctuation marking a question.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Inv
    -0.07
     instantaneous
    -0.07
    年龄
    -0.06
    Stick
    -0.06
     وات
    -0.06
    #End
    -0.06
    節
    -0.06
     Cra
    -0.06
     Friendship
    -0.06
    나
    -0.06
    POSITIVE LOGITS
    yme
    0.07
    υνα
    0.07
    �i
    0.07
    uspend
    0.06
    حل
    0.06
     tur
    0.06
     fence
    0.06
     validators
    0.06
    clamp
    0.06
    _customize
    0.06
    Act Density 0.064%

    No Known Activations