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

    Neuronpedia

    INDEX
    Explanations

    population statistics

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens containing decimal points (e.g. statistical percentages and fractional values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fibers
    -0.07
     predictable
    -0.06
    Snow
    -0.06
     станд
    -0.06
     arada
    -0.06
    products
    -0.06
    š
    -0.06
    istle
    -0.06
     bacteria
    -0.06
    (employee
    -0.06
    POSITIVE LOGITS
     ظ
    0.07
     rejo
    0.07
    OptionsMenu
    0.07
     ij
    0.07
    tab
    0.07
     ConfigureServices
    0.07
    Logout
    0.06
    edii
    0.06
     ''
↵
    0.06
    uzzy
    0.06
    Act Density 0.000%

    No Known Activations