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

    Neuronpedia

    INDEX
    Explanations

    is essentially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    трі
    0.45
    Obs
    0.41
    ➺
    0.41
    Чтобы
    0.40
    ṓ
    0.40
    려면
    0.40
     проти
    0.40
    Chois
    0.40
    ப்
    0.39
    0.38
    POSITIVE LOGITS
     yam
    0.47
     yum
    0.46
     অথবা
    0.43
     compact
    0.42
     oli
    0.42
     furent
    0.42
     souvenir
    0.42
     CRC
    0.41
     farewell
    0.41
     Muñoz
    0.41
    Act Density 0.001%

    No Known Activations