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 questions—tokens and turns that are part of user (or conversational) interrogative utterances.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     exert
    -0.07
    -0.07
    主业
    -0.06
    ayed
    -0.06
     trophies
    -0.06
    -0.06
     laid
    -0.06
     evidenced
    -0.06
     necessity
    -0.06
    .capture
    -0.06
    POSITIVE LOGITS
    arrivée
    0.07
     filmpjes
    0.07
    _ratings
    0.07
    ﰌ
    0.07
     paren
    0.07
    credible
    0.07
    /root
    0.07
     soma
    0.07
    .isOn
    0.07
     cocoa
    0.06
    Act Density 0.093%

    No Known Activations