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

    Neuronpedia

    INDEX
    Explanations

    sports teams' seasons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Log
    -0.07
    _device
    -0.07
    ")
↵
    -0.07
     trusting
    -0.07
    (application
    -0.07
    eta
    -0.06
     món
    -0.06
     ERROR
    -0.06
     earthly
    -0.06
     přep
    -0.06
    POSITIVE LOGITS
    σύ
    0.07
    .Redis
    0.07
     anzeigen
    0.06
     sạn
    0.06
    εβ
    0.06
    ея
    0.06
    Large
    0.06
    太
    0.06
    -we
    0.06
    ø
    0.06
    Act Density 0.013%

    No Known Activations