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

    Neuronpedia

    INDEX
    Explanations

    existence in various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     любые
    0.66
     the
    0.61
     any
    0.60
    任何
    0.59
    িনায়ক
    0.58
     your
    0.56
     this
    0.56
    濰
    0.55
    왤
    0.55
     никаких
    0.55
    POSITIVE LOGITS
     olduğunu
    0.70
    esini
    0.63
    。
    0.63
     olarak
    0.61
    ဖြစ်သည်။
    0.60
    そして
    0.59
     그리고
    0.59
     등을
    0.57
     bulunmaktadır
    0.56
    를
    0.56
    Act Density 0.005%

    No Known Activations