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

    Neuronpedia

    INDEX
    Explanations

    Expectations and requests

    np_max-act · gemini-2.0-flash

    The neuron fires on numerical expressions—especially money amounts and other digit‐based values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    database
    -0.06
     cụ
    -0.06
    ۰۰۰
    -0.06
     Wow
    -0.06
     imkan
    -0.06
     spinach
    -0.06
     subsidy
    -0.06
    Elite
    -0.06
     погод
    -0.06
     bring
    -0.06
    POSITIVE LOGITS
    ;(
    0.07
    .Primary
    0.07
    antd
    0.07
    _tensors
    0.07
     unravel
    0.06
    .factor
    0.06
     &(
    0.06
    BeforeEach
    0.06
     numel
    0.06
    ょ
    0.06
    Act Density 0.282%

    No Known Activations