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

    Neuronpedia

    INDEX
    Explanations

    Length

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    螌
    0.71
    peh
    0.64
     имуще
    0.62
     दोगु
    0.62
     मूल्यांकन
    0.62
    ству
    0.61
    妑
    0.61
    ίου
    0.60
     სამ
    0.59
    ಡೆಯ
    0.59
    POSITIVE LOGITS
     Length
    0.63
     length
    0.61
     semi
    0.60
     les
    0.59
     awk
    0.57
     junk
    0.56
     off
    0.55
     eso
    0.55
    length
    0.55
     Atkinson
    0.55
    Act Density 0.000%

    No Known Activations