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

    Neuronpedia

    INDEX
    Explanations

    Usage, distribution of content

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens and measurement values (especially decimals and figures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     бі
    -0.07
    antically
    -0.07
     communic
    -0.07
     DI
    -0.06
    movie
    -0.06
     wary
    -0.06
    (@
    -0.06
    architecture
    -0.06
     burglary
    -0.06
     under
    -0.06
    POSITIVE LOGITS
    ，看
    0.08
    acyj
    0.07
     คล
    0.06
    :black
    0.06
    ||
    0.06
    ]-
    0.06
    :A
    0.06
    ‌المللی
    0.06
     btc
    0.06
     şey
    0.06
    Act Density 0.276%

    No Known Activations