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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash

    The neuron is specialized for spotting numeric/math tokens—digits and arithmetic expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ضة
    -0.07
     }}↵
    -0.06
     Status
    -0.06
    uos
    -0.06
     setLoading
    -0.06
     Glad
    -0.06
     웨
    -0.06
     siblings
    -0.06
    드리
    -0.06
    +.
    -0.06
    POSITIVE LOGITS
     máte
    0.07
    .med
    0.07
    (&:
    0.07
     revamped
    0.07
    .sample
    0.07
    815
    0.06
     unavoidable
    0.06
     Hawai
    0.06
    因为
    0.06
     rigorous
    0.06
    Act Density 0.002%

    No Known Activations