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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INTERFACE
    -0.07
    .complete
    -0.06
    鉄道
    -0.06
    962
    -0.06
    ětí
    -0.06
     menu
    -0.06
    PagerAdapter
    -0.06
    372
    -0.06
    道路
    -0.06
    _transient
    -0.06
    POSITIVE LOGITS
     ﺍ
    0.07
    ufac
    0.07
    usher
    0.06
    ]!='
    0.06
     smoothing
    0.06
     prac
    0.06
    説明
    0.06
    updating
    0.06
     м
    0.06
     Units
    0.06
    Act Density 0.016%

    No Known Activations