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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect explicit date mentions (e.g., month names and day/year numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    izontal
    -0.07
     Imag
    -0.07
    CppCodeGen
    -0.07
    /Grid
    -0.06
     网
    -0.06
     WebDriverWait
    -0.06
     ware
    -0.06
     cuckold
    -0.06
    unts
    -0.06
     Cont
    -0.06
    POSITIVE LOGITS
    darwin
    0.07
    criteria
    0.07
     indulge
    0.07
     age
    0.07
     京
    0.06
     změny
    0.06
    Jan
    0.06
    -inch
    0.06
    expanded
    0.06
     treat
    0.06
    Act Density 0.025%

    No Known Activations