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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron detects numeric data and statistics, such as scores, team records, and decimal values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    しょ
    -0.07
    الش
    -0.07
     evacuated
    -0.07
     smart
    -0.07
     fault
    -0.06
    metis
    -0.06
     Finland
    -0.06
    _st
    -0.06
    million
    -0.06
     violated
    -0.06
    POSITIVE LOGITS
    roud
    0.08
     wiping
    0.07
    _CI
    0.07
    POR
    0.06
    Concurrency
    0.06
     tarn
    0.06
     yürüt
    0.06
     prejud
    0.06
    aturated
    0.06
    рів
    0.06
    Act Density 0.007%

    No Known Activations