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

    Neuronpedia

    INDEX
    Explanations

    AI disclaimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thoroughly
    0.74
    是非常
    0.71
    omo
    0.71
     để
    0.68
    ంటే
    0.68
     arbitrarily
    0.67
     መጠቀም
    0.67
    서는
    0.67
     zostało
    0.67
    是很
    0.66
    POSITIVE LOGITS
     Above
    0.87
    ，“
    0.82
    “.
    0.76
    “,
    0.74
     Tough
    0.74
     Game
    0.73
    身材
    0.73
    $-(
    0.73
     mercanc
    0.72
     Spill
    0.71
    Act Density 0.107%

    No Known Activations