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

    Neuronpedia

    INDEX
    Explanations

    scientific experiments

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is pick out language that describes quantitative measurement or evaluation in experimental methods and results.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -Cds
    -0.06
    Keywords
    -0.06
     rivalry
    -0.06
     benzer
    -0.06
     빌
    -0.06
    isOk
    -0.05
    autoload
    -0.05
    iameter
    -0.05
    fest
    -0.05
     dẫn
    -0.05
    POSITIVE LOGITS
    =settings
    0.07
     diabetes
    0.07
    <Integer
    0.07
     Listed
    0.07
     swing
    0.07
    .DataFrame
    0.06
     Nat
    0.06
    HAVE
    0.06
     Кал
    0.06
    Consumer
    0.06
    Act Density 0.080%

    No Known Activations