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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cols
    -0.07
     fuss
    -0.07
    _reverse
    -0.07
     económico
    -0.07
     Sect
    -0.07
    ích
    -0.06
    筋
    -0.06
    медицин
    -0.06
     motion
    -0.06
    dif
    -0.06
    POSITIVE LOGITS
     MainPage
    0.07
    league
    0.07
    ⊗
    0.07
    PRECATED
    0.07
     ws
    0.06
    /team
    0.06
    's
    0.06
     earnings
    0.06
     '*
    0.06
    森林公园
    0.06
    Act Density 0.001%

    No Known Activations