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

    Neuronpedia

    INDEX
    Explanations

    noun and its modifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getColumn
    0.55
     teorie
    0.55
    ερ
    0.53
     théorie
    0.52
    נס
    0.52
     teoría
    0.50
    Kelly
    0.49
    ய்ட
    0.49
    пу
    0.48
    лава
    0.48
    POSITIVE LOGITS
    (
    0.45
     Int
    0.39
    <sup>
    0.38
    ulph
    0.38
     distributes
    0.38
     dehydrogen
    0.37
     Berliner
    0.36
    kswagen
    0.36
    ivum
    0.36
     of
    0.36
    Act Density 0.000%

    No Known Activations