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

    Neuronpedia

    INDEX
    Explanations

    foreign language symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     computing
    0.42
     system
    0.41
     and
    0.41
     table
    0.39
     desktops
    0.39
     typography
    0.38
     computes
    0.38
    uisine
    0.38
    ها
    0.37
     compute
    0.37
    POSITIVE LOGITS
     이를
    0.45
    大丈夫
    0.45
     выну
    0.44
     বাদী
    0.41
     अपेक्षा
    0.41
     効果
    0.41
    咵
    0.41
    }.",
    0.40
    予以
    0.40
    䏹
    0.39
    Act Density 0.062%

    No Known Activations