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

    Neuronpedia

    INDEX
    Explanations

    Liu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atics
    -0.07
     notes
    -0.07
     noted
    -0.07
    博览
    -0.07
    营运
    -0.07
    Directed
    -0.07
    _disp
    -0.07
     related
    -0.07
    (orig
    -0.07
     движ
    -0.07
    POSITIVE LOGITS
    Lua
    0.07
    中场
    0.07
     Monsanto
    0.07
     neither
    0.07
     hakkı
    0.07
     accomp
    0.07
    ruitment
    0.06
    墙
    0.06
     Beacon
    0.06
    壸
    0.06
    Act Density 0.008%

    No Known Activations