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

    Neuronpedia

    INDEX
    Explanations

    turns

    np_max-act · gemini-2.0-flash

    This neuron detects numeric expressions—especially decimal numbers and other numeric tokens—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    диви
    -0.07
     दल
    -0.07
    raud
    -0.06
    اني
    -0.06
    _styles
    -0.06
     It
    -0.06
    kovi
    -0.06
    building
    -0.06
     uLocal
    -0.06
    It
    -0.06
    POSITIVE LOGITS
    šker
    0.06
     TIMER
    0.06
    smouth
    0.06
    nad
    0.06
    程
    0.06
    jedn
    0.06
    자를
    0.06
     Down
    0.06
     road
    0.06
    这是
    0.05
    Act Density 0.319%

    No Known Activations