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

    Neuronpedia

    INDEX
    Explanations

    size/magnitude

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric and related statistical tokens (e.g. numbers, percentages, “largest,” “markets”) that signal quantitative data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    онд
    -0.08
     Swinger
    -0.06
     incorporated
    -0.06
    anny
    -0.06
     censorship
    -0.06
    ظيف
    -0.06
    нивер
    -0.06
     Brandon
    -0.06
    /py
    -0.06
    тап
    -0.06
    POSITIVE LOGITS
     mutation
    0.08
     ladder
    0.06
     Mutation
    0.06
     dbName
    0.06
     Rotterdam
    0.06
     Relay
    0.06
     getChild
    0.06
    light
    0.06
     judgement
    0.06
     afford
    0.06
    Act Density 0.015%

    No Known Activations