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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point numeric literals (decimal fractions) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ちら
    -0.07
    ZA
    -0.06
     Hick
    -0.06
     Subscriber
    -0.06
     Albums
    -0.06
    trag
    -0.06
    Pu
    -0.06
     Toe
    -0.06
     パ
    -0.06
     Hay
    -0.06
    POSITIVE LOGITS
     Width
    0.07
    Gener
    0.06
     suoi
    0.06
    سب
    0.06
     спів
    0.06
    _zoom
    0.06
    ?-
    0.06
     duplication
    0.06
    ['_
    0.06
     arrest
    0.06
    Act Density 0.104%

    No Known Activations