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

    Neuronpedia

    INDEX
    Explanations

    code/data snippets

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by numeric tokens (digits and numbers) in structured or tabular text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Osama
    -0.07
    <Tag
    -0.06
    obao
    -0.06
    ETweet
    -0.06
    IndexOf
    -0.06
     petals
    -0.06
     heyec
    -0.06
    Delivery
    -0.06
     trải
    -0.06
    Severity
    -0.06
    POSITIVE LOGITS
     stabilization
    0.06
     ($_
    0.06
    ฬ
    0.06
    :value
    0.06
     contested
    0.06
    }')
    0.06
    high
    0.06
    ///
    0.06
    =?
    0.06
    _nums
    0.06
    Act Density 0.010%

    No Known Activations