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

    Neuronpedia

    INDEX
    Explanations

    Questions and knowledge

    np_max-act · gemini-2.0-flash

    This neuron primarily detects question or inquiry cues—especially “what,” “how,” or “why” in contexts where something is being asked or explained.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     twin
    -0.06
     registrado
    -0.06
    Вы
    -0.06
     قتل
    -0.06
    �
    -0.06
     Blackjack
    -0.06
    �
    -0.06
    wing
    -0.06
    CriticalSection
    -0.06
     DR
    -0.06
    POSITIVE LOGITS
     bulun
    0.08
    ^
    0.07
     эти
    0.07
     �
    0.07
     republic
    0.07
     refute
    0.07
     spokesman
    0.06
    Chooser
    0.06
    svg
    0.06
    ��态
    0.06
    Act Density 0.181%

    No Known Activations