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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ል
    -0.08
    alex
    -0.08
     Starts
    -0.07
    <std
    -0.07
     Laurent
    -0.07
    ịnh
    -0.07
    normalize
    -0.07
     troubles
    -0.07
     flush
    -0.07
    等方面的
    -0.07
    POSITIVE LOGITS
     pilot
    0.08
     employee
    0.07
     đình
    0.07
     operative
    0.07
    خف
    0.07
    牁
    0.07
    小姐
    0.07
    כ
    0.07
     midd
    0.07
    riers
    0.07
    Act Density 0.016%

    No Known Activations