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

    Neuronpedia

    INDEX
    Explanations

    Numbers and quantities

    np_max-act · gemini-2.0-flash

    The neuron is tuned to spot numeric expressions (digits, monetary amounts, counts, durations, etc.) within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cath
    -0.06
     rebellion
    -0.06
    ,options
    -0.06
    	array
    -0.06
     corres
    -0.06
     Attach
    -0.06
    shop
    -0.06
     advertisements
    -0.06
     راه
    -0.06
    (interval
    -0.06
    POSITIVE LOGITS
    imid
    0.07
    ां
    0.06
    uja
    0.06
    qh
    0.06
    -times
    0.06
     centrally
    0.06
    cai
    0.06
    ading
    0.06
    因
    0.06
     detective
    0.06
    Act Density 0.125%

    No Known Activations