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

    Neuronpedia

    INDEX
    Explanations

    phrases involving legal terminology and procedural language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows the word "of" or "in"

    np_acts-logits-general · gemini-2.0-flash

    various productions, different types of life, ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    -0.63
     Wikimedijinoj
    -0.63
    something
    -0.62
    tanleria
    -0.60
     something
    -0.60
     was
    -0.56
    was
    -0.54
     kasarigan
    -0.53
    кипедия
    -0.52
    Personendaten
    -0.52
    POSITIVE LOGITS
     مختلف
    1.13
     different
    0.99
     various
    0.95
     unterschied
    0.92
     المختلفة
    0.91
     lesquelles
    0.90
    different
    0.90
     forskjellige
    0.88
     poszczegól
    0.87
     ulike
    0.86
    Act Density 0.842%

    No Known Activations