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

    Neuronpedia

    INDEX
    Explanations

    lists of facts and forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    接触
    0.44
    лм
    0.44
     (!(
    0.42
    ゥ
    0.42
    ્ઞ
    0.42
     deflect
    0.41
    ীদার
    0.40
    呎
    0.40
    ͙
    0.39
    定位
    0.39
    POSITIVE LOGITS
     อยู่
    0.49
    خود
    0.47
    јединачна
    0.46
    이고
    0.44
    ৩৭
    0.44
     लिं
    0.43
    éph
    0.43
    lym
    0.42
    YOU
    0.41
    وذ
    0.41
    Act Density 0.004%

    No Known Activations