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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rahul
    -0.07
    หย
    -0.07
     NotImplementedException
    -0.06
     Shin
    -0.06
     ศร
    -0.06
     wrapping
    -0.06
    전에
    -0.06
    (@"%@",
    -0.06
     Foam
    -0.06
    ('*',
    -0.06
    POSITIVE LOGITS
    /\
    0.07
     ))↵↵
    0.07
     pourrait
    0.07
    //}↵↵
    0.06
     hands
    0.06
     COUR
    0.06
     Đài
    0.06
    ...)↵
    0.06
     比
    0.06
     matters
    0.06
    Act Density 0.008%

    No Known Activations