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

    Neuronpedia

    INDEX
    Explanations

    multilingual article identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tightly
    0.43
    quality
    0.43
    ('${
    0.41
    o
    0.41
    y
    0.40
    A
    0.40
    filter
    0.39
     tight
    0.39
     steel
    0.38
    sync
    0.38
    POSITIVE LOGITS
     Foreground
    0.48
     אחר
    0.48
     канди
    0.44
     నేను
    0.43
    蕤
    0.42
     જવાબ
    0.42
     thửa
    0.41
     ძალი
    0.41
    飴
    0.41
     божо
    0.41
    Act Density 0.002%

    No Known Activations