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

    Neuronpedia

    INDEX
    Explanations

    Legal/Medical context

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on words naming medical specialties or practitioners (e.g. “urologia,” “urologistas,” “médicos”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -white
    -0.06
    Conn
    -0.06
     awards
    -0.06
     Drupal
    -0.06
    bpp
    -0.06
     possessions
    -0.06
    $max
    -0.05
    _letters
    -0.05
    bars
    -0.05
    Drupal
    -0.05
    POSITIVE LOGITS
    ?";↵
    0.07
    VERTISE
    0.07
    лия
    0.06
    -G
    0.06
    Lista
    0.06
     timetable
    0.06
     intimately
    0.06
    娱乐
    0.06
    做
    0.06
    >B
    0.06
    Act Density 0.002%

    No Known Activations