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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash

    The neuron primarily detects numerical tokens and numeric expressions (e.g. measurements, percentages, decimals, units).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gon
    -0.08
     Mour
    -0.07
     ανα
    -0.06
     CHANNEL
    -0.06
    GPS
    -0.06
    、ア
    -0.06
    Dear
    -0.06
     KE
    -0.06
     hour
    -0.06
    去
    -0.06
    POSITIVE LOGITS
    ufreq
    0.06
    �江
    0.06
     своей
    0.06
     сб
    0.06
    ักด
    0.06
    /company
    0.06
    Hold
    0.06
     compromising
    0.06
     fileprivate
    0.06
    wins
    0.06
    Act Density 0.242%

    No Known Activations