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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    This neuron fires on identifiers referring to library or built-in functions and methods (e.g. String, parseFloat, Math.max, require, table.insert).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ADF
    -0.08
     รวม
    -0.07
    ंब
    -0.06
    ाब
    -0.06
    玉
    -0.06
    PL
    -0.06
    ventional
    -0.06
     enduring
    -0.06
     Điều
    -0.06
     landlords
    -0.06
    POSITIVE LOGITS
     shocked
    0.06
    γκα
    0.06
     교육
    0.06
    軽
    0.06
    ajar
    0.06
    Clean
    0.06
    chef
    0.06
    ฬ
    0.06
     itinerary
    0.06
    _Entry
    0.06
    Act Density 0.005%

    No Known Activations