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

    Neuronpedia

    INDEX
    Explanations

    article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arcs
    -0.08
     lobster
    -0.07
    -eyed
    -0.07
     mold
    -0.07
    _Anim
    -0.06
     Range
    -0.06
     pulses
    -0.06
     vamp
    -0.06
    pering
    -0.06
     formatted
    -0.06
    POSITIVE LOGITS
     Classe
    0.07
    ъек
    0.06
     três
    0.06
    中华
    0.06
    nictvím
    0.06
    Favorite
    0.06
     expérience
    0.06
     İ
    0.06
     ]),↵
    0.06
     Counties
    0.06
    Act Density 0.654%

    No Known Activations