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

    Neuronpedia

    INDEX
    Explanations

    Periods

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on numeric tokens and quantified expressions (e.g., numbers, decimals, measurements, and reference indices).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mismo
    -0.07
     無
    -0.07
     Vertical
    -0.06
    住
    -0.06
     kid
    -0.06
    학생
    -0.06
    约
    -0.06
    �
    -0.06
     Smile
    -0.06
    _strength
    -0.06
    POSITIVE LOGITS
    -Assad
    0.06
    стор
    0.06
    !!.
    0.06
    欧
    0.06
     crowded
    0.06
    -oper
    0.06
     UIGraphics
    0.06
    了解
    0.06
    โลก
    0.06
    -ext
    0.06
    Act Density 0.223%

    No Known Activations