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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Messages
    -0.07
    _unregister
    -0.07
     replies
    -0.06
     github
    -0.06
    _by
    -0.06
     cheapest
    -0.06
    _urls
    -0.06
    _PY
    -0.06
    isp
    -0.06
    VI
    -0.06
    POSITIVE LOGITS
    phalt
    0.06
     вар
    0.06
    므로
    0.06
     возникнов
    0.06
     законодатель
    0.06
    álně
    0.06
     соблюд
    0.06
     εισ
    0.06
     Ев
    0.06
     приобрет
    0.06
    Act Density 0.028%

    No Known Activations