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

    Neuronpedia

    INDEX
    Explanations

    header

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that specify pandas .read_csv() parameters (e.g. header=None, parse_dates, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    amphetamine
    -0.07
    ovolta
    -0.07
    Suc
    -0.07
    	Public
    -0.06
     PUSH
    -0.06
    ąd
    -0.06
    rances
    -0.06
     electromagnetic
    -0.06
    ест
    -0.06
     call
    -0.06
    POSITIVE LOGITS
    ListAdapter
    0.07
     biliyor
    0.06
     прибор
    0.06
     whatsoever
    0.06
    hift
    0.06
    .jdesktop
    0.06
     wherever
    0.06
     درباره
    0.06
    .BackgroundColor
    0.06
    shire
    0.06
    Act Density 0.004%

    No Known Activations