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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    information related to financial performance and market analysis.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on numeric tokens—digits, percentages, or other number-like terms in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     paranormal
    -0.06
     بندی
    -0.06
     vacuum
    -0.06
     Bolton
    -0.06
     basal
    -0.06
    	Token
    -0.06
    	response
    -0.06
     callee
    -0.05
     Million
    -0.05
     Greene
    -0.05
    POSITIVE LOGITS
    summary
    0.07
    IDEO
    0.07
    ="//
    0.07
    éri
    0.07
     HISTORY
    0.07
    /npm
    0.07
     tw
    0.07
     tarihi
    0.06
     cocks
    0.06
    ическая
    0.06
    Act Density 0.022%

    No Known Activations