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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    遨
    -0.07
    猪肉
    -0.07
    ᗯ
    -0.07
    ваться
    -0.07
    赖以
    -0.07
    婚姻
    -0.06
    חיפ
    -0.06
    之间的
    -0.06
    (rel
    -0.06
     volcanic
    -0.06
    POSITIVE LOGITS
    你喜欢
    0.07
    Ǯ
    0.07
     redirects
    0.07
    .writer
    0.06
     closes
    0.06
     initializing
    0.06
    EGA
    0.06
    ,’
    0.06
     having
    0.06
    ﱉ
    0.06
    Act Density 0.005%

    No Known Activations