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

    Neuronpedia

    INDEX
    Explanations

    percentages

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on floating‐point numeric tokens (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    medical terms related to diseases and their physiological implications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     CCD
    -0.06
    layan
    -0.06
    架
    -0.06
    usto
    -0.06
    ısıyla
    -0.06
    Disposition
    -0.06
    cole
    -0.06
     pedals
    -0.06
     微
    -0.06
    192
    -0.06
    POSITIVE LOGITS
    ,double
    0.07
     kommt
    0.06
    ught
    0.06
    _firstname
    0.06
    ув
    0.06
    mongo
    0.06
    	init
    0.06
    .subscription
    0.06
    ()+
    0.06
     przypad
    0.06
    Act Density 0.035%

    No Known Activations