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

    Neuronpedia

    INDEX
    Explanations

    story titles and scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.55
    im
    0.49
    un
    0.49
    to
    0.48
    utf
    0.46
    p
    0.46
     primeros
    0.45
     eighty
    0.44
    his
    0.43
    begin
    0.42
    POSITIVE LOGITS
    📵
    0.51
     смартфо
    0.49
    ✅
    0.49
    ➷
    0.49
    单一
    0.48
     ALERT
    0.47
    穼
    0.46
     ✔
    0.46
    文件夹
    0.45
    तमंद
    0.45
    Act Density 0.008%

    No Known Activations