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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash

    This neuron lights up on tokens that signal a question—especially question marks and question‐tag words (e.g. “?” or “right?”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _public
    -0.06
     bandwidth
    -0.06
     fundamentals
    -0.06
     Formatter
    -0.06
    itors
    -0.06
    .errorMessage
    -0.06
    {};↵
    -0.06
     instantiated
    -0.06
    chars
    -0.06
    _MAG
    -0.06
    POSITIVE LOGITS
    分布
    0.07
    .HandleFunc
    0.07
    .GroupBox
    0.06
    ']).
    0.06
     Ale
    0.06
    _registry
    0.06
    NES
    0.06
     edil
    0.06
     possibly
    0.06
    �
    0.06
    Act Density 0.038%

    No Known Activations