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

    Neuronpedia

    INDEX
    Explanations

    code structure and file handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     매우
    0.39
    MDg
    0.35
    Assured
    0.34
     ಸುತ್ತ
    0.34
     ಸ್ಟ
    0.33
     اسكت
    0.33
     πολύ
    0.32
    菪
    0.32
     fluoro
    0.32
    <unused1059>
    0.32
    POSITIVE LOGITS
     when
    0.43
    ;
    0.43
     cuando
    0.43
    ;"
    0.40
    );
    0.39
     и
    0.39
     and
    0.39
     ,
    0.39
     (
    0.37
    への
    0.37
    Act Density 0.067%

    No Known Activations