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

    Neuronpedia

    INDEX
    Explanations

    sports wins

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (especially years and other multi-digit numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .windows
    -0.07
     temin
    -0.06
     anthology
    -0.06
    GEN
    -0.06
    .support
    -0.06
    ')['
    -0.06
    包含
    -0.06
    AFF
    -0.06
    .Ex
    -0.06
     potassium
    -0.06
    POSITIVE LOGITS
    [args
    0.07
    мін
    0.07
     sentiments
    0.07
     действия
    0.06
    !
    0.06
    stack
    0.06
     liberties
    0.06
    졌
    0.06
    mouseover
    0.06
     Jihad
    0.06
    Act Density 0.024%

    No Known Activations