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

    Neuronpedia

    INDEX
    Explanations

    meaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abetes
    -0.63
    turnstile
    -0.61
     कैसी
    -0.61
    </caption>
    -0.60
    roek
    -0.59
    Affected
    -0.59
    tonsoft
    -0.58
     []:
    -0.57
    meant
    -0.54
    UMBIA
    -0.53
    POSITIVE LOGITS
     the
    1.01
     a
    0.75
     it
    0.75
    <bos>
    0.73
     that
    0.70
     you
    0.69
     their
    0.63
     your
    0.61
     our
    0.56
     an
    0.56
    Act Density 0.035%

    No Known Activations