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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on tokens containing numeric information—years, measurements, counts, ordinals, and other digit-based expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    $j
    -0.07
     k
    -0.07
     siyasi
    -0.07
    ुपय
    -0.07
     bikes
    -0.06
    多い
    -0.06
    })
↵
↵
    -0.06
    ']))
↵
    -0.06
    ीफ
    -0.06
     BEFORE
    -0.06
    POSITIVE LOGITS
     Predator
    0.08
    (age
    0.07
     Conversion
    0.06
     Blueprint
    0.06
    oucher
    0.06
     Increment
    0.06
    -print
    0.06
    .googleapis
    0.06
     BUG
    0.06
     hass
    0.06
    Act Density 0.503%

    No Known Activations