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

    Neuronpedia

    INDEX
    Explanations

    file extensions

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of PDF files, especially occurrences of “.pdf” or “PDF.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     поход
    -0.07
    WER
    -0.07
    erdem
    -0.06
    _un
    -0.06
    /connect
    -0.06
    deal
    -0.06
    .POST
    -0.06
     argparse
    -0.06
    urls
    -0.06
     POST
    -0.06
    POSITIVE LOGITS
     devoid
    0.07
    ()}}↵
    0.07
    ój
    0.06
     ö
    0.06
     mod
    0.06
    acji
    0.06
     MSM
    0.06
     resid
    0.06
    @endsection
    0.06
     kli
    0.06
    Act Density 0.012%

    No Known Activations