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

    Neuronpedia

    INDEX
    Explanations

    answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ังหว
    0.47
     anxieties
    0.46
     calculations
    0.42
     //!
    0.42
     mérite
    0.42
     subtleties
    0.41
     stools
    0.41
     amateurs
    0.40
    是否有
    0.40
     কেমন
    0.40
    POSITIVE LOGITS
     Answer
    0.72
    Answer
    0.71
    They
    0.68
     They
    0.68
     Answers
    0.66
    ANSWER
    0.66
    答案
    0.64
    they
    0.63
     Yes
    0.62
    Yes
    0.62
    Act Density 0.031%

    No Known Activations