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

    Neuronpedia

    INDEX
    Explanations

    200

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens (especially date and number references such as years, filing dates, and numbered identifiers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     wł
    -0.07
     بیان
    -0.07
     tý
    -0.07
     stimuli
    -0.07
     Mal
    -0.06
     pohled
    -0.06
     Saras
    -0.06
     lcd
    -0.06
     Що
    -0.06
     Cream
    -0.06
    POSITIVE LOGITS
    πή
    0.06
    Typed
    0.06
    patial
    0.06
    Assignable
    0.06
     ін
    0.06
     찾
    0.06
     serviceProvider
    0.06
    _ARGS
    0.06
     migrated
    0.06
    ايي
    0.05
    Act Density 0.002%

    No Known Activations