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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron fires on detailed numeric measurements (especially decimal‐format values) in technical descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    mitted
    -0.07
     pow
    -0.06
    .med
    -0.06
    ,min
    -0.06
    bred
    -0.06
    activex
    -0.06
    زي
    -0.06
    RequestMethod
    -0.06
     defaultdict
    -0.06
    012
    -0.06
    POSITIVE LOGITS
    \'
    0.07
     Juli
    0.06
     Steph
    0.06
    (pop
    0.06
     Snapdragon
    0.06
     appare
    0.06
     إل
    0.06
     мень
    0.06
    Dur
    0.06
    Sele
    0.06
    Act Density 0.412%

    No Known Activations