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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric measurement tokens—quantitative figures (numbers and their units) that report experimental or performance values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rightful
    -0.07
    وزی
    -0.07
    ική
    -0.07
     archived
    -0.06
    界
    -0.06
    ิต
    -0.06
    Evt
    -0.06
    ynamics
    -0.06
    _profiles
    -0.06
    andre
    -0.06
    POSITIVE LOGITS
    รษ
    0.07
     अग
    0.06
    STRU
    0.06
     particular
    0.06
    .reshape
    0.06
    dbl
    0.06
    pNext
    0.06
    .URL
    0.06
    .str
    0.06
     buys
    0.06
    Act Density 0.049%

    No Known Activations