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

    Neuronpedia

    INDEX
    Explanations

    Academic texts

    np_max-act · gemini-2.0-flash

    The neuron activates on author names in academic citations (e.g., “Schilling,” “Olson,” “Bolin”) and related reference metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ::*
    -0.07
    requirements
    -0.06
    916
    -0.06
     applied
    -0.06
    500
    -0.06
    917
    -0.06
     сад
    -0.06
    ller
    -0.06
     interpreting
    -0.06
     нада
    -0.06
    POSITIVE LOGITS
    lassen
    0.06
     recipient
    0.06
     причины
    0.06
    akistan
    0.06
    flamm
    0.06
    (&___
    0.06
     fueron
    0.06
     PHYS
    0.06
    ливо
    0.06
     Xen
    0.06
    Act Density 0.019%

    No Known Activations