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

    Neuronpedia

    INDEX
    Explanations

    completeness and entirety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.29
    '،
    0.28
    ება
    0.27
    లిన
    0.27
    ა
    0.27
    णार्‍या
    0.26
    雋
    0.26
    ir
    0.26
     berths
    0.26
     Бүгенге
    0.26
    POSITIVE LOGITS
    ong
    0.29
     of
    0.28
     (
    0.25
    с
    0.25
    зне
    0.23
    سين
    0.22
    I
    0.22
    0.20
    ス
    0.20
    (
    0.20
    Act Density 0.256%

    No Known Activations