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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric measurements—especially numbers in parentheses—such as durations, concentrations, temperatures, or other quantitative values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     plasma
    -0.07
    _IList
    -0.06
    <Resource
    -0.06
    istributor
    -0.06
    านคร
    -0.06
    Builders
    -0.06
    Linked
    -0.06
    Modes
    -0.06
    :hidden
    -0.06
    ้องการ
    -0.06
    POSITIVE LOGITS
     People
    0.08
    :e
    0.07
     jedná
    0.07
     Porn
    0.07
     Pearson
    0.06
    oks
    0.06
     Colon
    0.06
     crime
    0.06
     �
    0.06
     provincia
    0.06
    Act Density 0.029%

    No Known Activations