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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—digits, decimals, percentages, and other numbers—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Testing
    -0.07
    Stroke
    -0.07
    placed
    -0.07
    ző
    -0.06
    -k
    -0.06
    ,n
    -0.06
    linha
    -0.06
     indem
    -0.06
    death
    -0.06
    -death
    -0.06
    POSITIVE LOGITS
     pstmt
    0.07
     ấn
    0.07
    .MAIN
    0.07
     Nass
    0.06
    _RM
    0.06
    .Default
    0.06
    _LONG
    0.06
    र
    0.06
    ATEST
    0.06
    Narr
    0.06
    Act Density 0.065%

    No Known Activations