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

    Neuronpedia

    INDEX
    Explanations

    say "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -security
    -0.07
     başında
    -0.07
    DAT
    -0.07
    -resource
    -0.07
    Comment
    -0.07
     mapped
    -0.06
     learned
    -0.06
     teaching
    -0.06
     demo
    -0.06
    设备
    -0.06
    POSITIVE LOGITS
     Кра
    0.06
     hilar
    0.06
    uff
    0.06
     Cologne
    0.06
     Brno
    0.06
     Propel
    0.06
    ZA
    0.06
    -ob
    0.06
     NotImplementedError
    0.06
     Сем
    0.06
    Act Density 0.029%

    No Known Activations