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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    》。
    0.51
     क्योंकि
    0.48
     ہے۔
    0.47
    这也是
    0.46
    `.
    0.45
    ’।
    0.45
     کیونکہ
    0.44
    ².
    0.44
    ܀
    0.44
    %.
    0.44
    POSITIVE LOGITS
     did
    0.73
     had
    0.70
     does
    0.60
     insists
    0.58
     chooses
    0.57
     got
    0.56
     gave
    0.55
     strives
    0.55
     tries
    0.54
     prides
    0.54
    Act Density 0.074%

    No Known Activations