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

    Neuronpedia

    INDEX
    Explanations

    comparisons and differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nonetheless
    -0.32
     nevertheless
    -0.31
    testCase
    -0.29
    没åħ³ç³»
    -0.28
    ä¸įå½±åĵį
    -0.28
    usable
    -0.26
    TestCase
    -0.25
    èĢĥéªĮ
    -0.24
    ulous
    -0.24
    иÑģк
    -0.24
    POSITIVE LOGITS
    pla
    0.28
    æĶ¿
    0.27
    çļĻ
    0.26
    ande
    0.25
     datatype
    0.24
    å¾Ĺåĩº
    0.24
    /control
    0.24
    åĬłä¹ĭ
    0.24
    аÑĪ
    0.24
    charts
    0.24
    Act Density 0.123%

    No Known Activations