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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that mark dates, years, and other numerical career‐timeline references in a biography.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cos
    -0.07
     〈
    -0.07
    icina
    -0.07
     Emp
    -0.06
    uit
    -0.06
    NK
    -0.06
    /mit
    -0.06
    ikes
    -0.06
    illas
    -0.06
     Thursday
    -0.06
    POSITIVE LOGITS
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    0.07
    247
    0.07
    [dim
    0.06
     Warn
    0.06
     getState
    0.06
    =\"$
    0.06
    <class
    0.06
    	window
    0.06
    .savefig
    0.06
    ίναι
    0.06
    Act Density 0.042%

    No Known Activations