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

    Neuronpedia

    INDEX
    Explanations

    Dates/centuries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     автомати
    -0.07
     checkpoints
    -0.07
    ům
    -0.06
     yapılması
    -0.06
     salsa
    -0.06
    -General
    -0.06
    (\"
    -0.06
     mh
    -0.06
    HomePage
    -0.06
     комп
    -0.06
    POSITIVE LOGITS
    KW
    0.06
     filme
    0.06
     जब
    0.06
     hai
    0.06
    нение
    0.06
     ring
    0.06
    ��
    0.06
    lake
    0.06
    gather
    0.06
    ool
    0.06
    Act Density 0.049%

    No Known Activations