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

    Neuronpedia

    INDEX
    Explanations

    200

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing floating‐point values (decimal fractions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Marilyn
    -0.07
     Winning
    -0.06
    ñana
    -0.06
    	onClick
    -0.06
    มาร
    -0.06
     offsetof
    -0.06
    унд
    -0.06
    oples
    -0.06
    	sizeof
    -0.06
    )(((
    -0.06
    POSITIVE LOGITS
    enddate
    0.07
     quantitative
    0.07
    ством
    0.07
    ::_('
    0.07
     recib
    0.07
    [result
    0.06
     society
    0.06
     investigación
    0.06
     Scientific
    0.06
     нали
    0.06
    Act Density 0.002%

    No Known Activations