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

    Neuronpedia

    INDEX
    Explanations

    -ended

    np_max-act · gemini-2.0-flash

    The neuron responds to the term “open-ended,” effectively detecting mentions of open-ended questions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     borrowing
    -0.07
     Indices
    -0.07
     blok
    -0.07
     Popup
    -0.07
    "\↵
    -0.06
     mob
    -0.06
     ();
↵
    -0.06
     Menu
    -0.06
     voltage
    -0.06
    )['
    -0.06
    POSITIVE LOGITS
    <(),
    0.07
    ระหว
    0.07
     inertia
    0.07
    oui
    0.07
     curved
    0.06
     jinak
    0.06
    -Za
    0.06
    ังค
    0.06
    ogenesis
    0.06
    όρ
    0.06
    Act Density 0.003%

    No Known Activations