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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    The neuron is triggered by floating-point numeric literals (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     movie
    -0.07
    .Step
    -0.06
    典
    -0.06
     محمود
    -0.06
    -cl
    -0.06
     Bernard
    -0.06
    絵
    -0.06
    (rot
    -0.06
    でしょう
    -0.06
     avoiding
    -0.06
    POSITIVE LOGITS
    ализи
    0.07
    Fourth
    0.07
     ',
    0.06
    sher
    0.06
    orthy
    0.06
     Yamaha
    0.06
    udp
    0.06
     cones
    0.06
    _lcd
    0.06
    659
    0.06
    Act Density 0.023%

    No Known Activations