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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric values, especially decimal numbers and other quantitative figures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     универ
    -0.07
     Yield
    -0.06
    家族
    -0.06
    _byte
    -0.06
     Moist
    -0.06
     word
    -0.06
     dialect
    -0.06
     preset
    -0.06
    لمة
    -0.06
    Ranges
    -0.06
    POSITIVE LOGITS
    western
    0.08
    relude
    0.06
     IPA
    0.06
    ُه
    0.06
     vip
    0.06
    .querySelectorAll
    0.06
    غة
    0.06
     standout
    0.06
    _UNSUPPORTED
    0.06
     monde
    0.06
    Act Density 0.139%

    No Known Activations