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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    content related to health insurance and medical coverage options.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects numbered step markers—i.e. tokens that are digits used to label steps in instructions (like “1”, “2”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .pause
    -0.07
    _cells
    -0.07
    _elements
    -0.07
    通常
    -0.06
    ui
    -0.06
    -wall
    -0.06
    ≥
    -0.06
    ्रद
    -0.06
     거의
    -0.06
    HUD
    -0.06
    POSITIVE LOGITS
     cerca
    0.07
    거래
    0.07
     Mb
    0.07
     siguiente
    0.06
    ernes
    0.06
     countertops
    0.06
    ND
    0.06
     disappoint
    0.06
     pohled
    0.06
    ENDOR
    0.06
    Act Density 0.653%

    No Known Activations