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
    前的
    -0.07
     Пр
    -0.06
    移
    -0.06
     verilen
    -0.06
     úprav
    -0.06
    assignment
    -0.06
    б
    -0.06
    なお
    -0.06
    ('_
    -0.06
    [pos
    -0.06
    POSITIVE LOGITS
     DE
    0.09
     nieuwe
    0.07
    (){↵↵
    0.06
    inous
    0.06
    eguard
    0.06
    ！↵↵
    0.06
    _UTILS
    0.06
     accelerating
    0.06
    acak
    0.06
    @section
    0.06
    Act Density 0.057%

    No Known Activations