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

    Neuronpedia

    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash

    This neuron detects interrogative cues—tokens that signal a user question (e.g. what, when, ask, why).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     />)↵
    -0.06
     роб
    -0.06
     Пів
    -0.06
    ्कर
    -0.06
     Zy
    -0.06
    icious
    -0.06
    акон
    -0.06
    translator
    -0.06
    warz
    -0.06
    Tour
    -0.06
    POSITIVE LOGITS
    Transparent
    0.06
     pageNo
    0.06
    .ReadString
    0.06
     cdr
    0.06
    specialchars
    0.06
    /Runtime
    0.06
     Coordinate
    0.06
    Height
    0.06
     mismatch
    0.06
    (Source
    0.06
    Act Density 0.031%

    No Known Activations