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

    Neuronpedia

    INDEX
    Explanations

    sports seasons

    np_max-act · gemini-2.0-flash

    This neuron detects numeric and statistical tokens—especially years, counts, and sports‐career figures—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    gone
    -0.07
    Why
    -0.07
     Swarm
    -0.06
     Sofia
    -0.06
     của
    -0.06
     convolution
    -0.06
    Thumb
    -0.06
    nod
    -0.06
    Thumbnail
    -0.06
     Est
    -0.06
    POSITIVE LOGITS
     трохи
    0.06
     velký
    0.06
    lw
    0.06
     muži
    0.06
    ει
    0.06
    >xpath
    0.06
     همچ
    0.06
     proletariat
    0.06
     루
    0.06
    ráci
    0.06
    Act Density 0.020%

    No Known Activations