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

    Neuronpedia

    INDEX
    Explanations

    universities and students

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     West
    -0.07
    etě
    -0.06
     Syn
    -0.06
     deleg
    -0.06
    niej
    -0.06
     när
    -0.06
    oro
    -0.06
     Modifier
    -0.06
    Sr
    -0.06
    _AMD
    -0.06
    POSITIVE LOGITS
     [@
    0.07
    crease
    0.06
     гем
    0.06
    liğ
    0.06
    幹
    0.06
    bose
    0.06
     �
    0.06
    enabled
    0.06
    比赛
    0.06
    .headers
    0.06
    Act Density 0.018%

    No Known Activations