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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outs
    0.49
     caps
    0.43
    นต์
    0.42
     mozz
    0.39
     AVL
    0.39
    ណ្ត
    0.39
    axo
    0.38
     synced
    0.38
    utes
    0.38
     decoupled
    0.38
    POSITIVE LOGITS
     Díaz
    0.56
     ی
    0.52
     моло
    0.50
    yielding
    0.48
    ي
    0.47
    பொ
    0.47
    ﻴ
    0.46
    Diaz
    0.46
     Yardım
    0.45
    س
    0.45
    Act Density 0.000%

    No Known Activations