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

    Neuronpedia

    INDEX
    Explanations

    : ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olid
    -0.07
     DAG
    -0.07
     Μα
    -0.06
     Johann
    -0.06
     leakage
    -0.06
     WAS
    -0.06
    [Test
    -0.06
    GREE
    -0.06
    Analysis
    -0.06
     Прот
    -0.06
    POSITIVE LOGITS
    :])↵
    0.08
    :]↵
    0.07
    [::-
    0.07
    없이
    0.06
    :],
    0.06
    衣
    0.06
     Spanish
    0.06
    :]:↵
    0.06
     دیگر
    0.06
    ivec
    0.06
    Act Density 0.003%

    No Known Activations