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

    Neuronpedia

    INDEX
    Explanations

    will not encryption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ui
    0.49
     UI
    0.49
     db
    0.46
     Cd
    0.45
    es
    0.44
     अहमदाबाद
    0.44
     van
    0.44
    0.44
     console
    0.43
     brackets
    0.43
    POSITIVE LOGITS
    ل
    0.52
    ตัน
    0.48
    LongNumber
    0.48
    то
    0.47
    نګ
    0.47
    Tens
    0.45
    𝐭
    0.45
    isième
    0.45
    طان
    0.45
    ти
    0.44
    Act Density 0.004%

    No Known Activations