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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing non‐integer (floating‐point) values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    National
    -0.07
     National
    -0.06
    urances
    -0.06
    етич
    -0.06
     determines
    -0.06
    的地
    -0.06
     entering
    -0.06
     가격
    -0.06
    elan
    -0.06
    존
    -0.06
    POSITIVE LOGITS
    .keyCode
    0.08
    .MessageBox
    0.07
    _TRUNC
    0.07
     یافته
    0.06
    [T
    0.06
     теор
    0.06
     Establish
    0.06
    (Product
    0.06
    ่ต
    0.06
    ModelProperty
    0.06
    Act Density 0.051%

    No Known Activations