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

    Neuronpedia

    INDEX
    Explanations

    income

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (especially decimal and integer numbers in the demographic/statistics data).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _SPE
    -0.06
    emetery
    -0.06
     pair
    -0.06
     گفت
    -0.06
     ymin
    -0.06
    enek
    -0.06
     سید
    -0.06
    con
    -0.06
     Cour
    -0.06
    radius
    -0.06
    POSITIVE LOGITS
     sıkıntı
    0.08
     등장
    0.07
     Leigh
    0.07
    /year
    0.06
    Stripe
    0.06
     Minority
    0.06
     CLEAN
    0.06
     برابر
    0.06
     Chí
    0.06
     Muj
    0.06
    Act Density 0.000%

    No Known Activations