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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Say
    -0.06
     livre
    -0.06
     áreas
    -0.06
    alım
    -0.06
    ließlich
    -0.06
    raně
    -0.06
    )\<
    -0.06
     fool
    -0.06
    定义
    -0.06
    )↵↵↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
    :user
    0.07
    _relu
    0.06
     Bale
    0.06
     granted
    0.06
    windows
    0.06
     span
    0.06
    ////////
    0.06
    Bachelor
    0.06
    _part
    0.06
    difference
    0.06
    Act Density 0.010%

    No Known Activations