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

    Neuronpedia

    INDEX
    Explanations

    operation

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially version numbers, dates, IDs, and other multi‐digit/decimal sequences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    效
    -0.07
    CONT
    -0.06
     Rogers
    -0.06
     کش
    -0.06
     soon
    -0.06
    Slider
    -0.06
     worst
    -0.06
     Newton
    -0.06
    .dup
    -0.06
    UIFont
    -0.06
    POSITIVE LOGITS
     десяти
    0.07
    ermalink
    0.07
    .Can
    0.07
    ρωση
    0.07
     сім
    0.06
    _WATER
    0.06
    Accessible
    0.06
     возможно
    0.06
     OC
    0.06
    InputDialog
    0.06
    Act Density 0.029%

    No Known Activations