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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uk
    2.39
    ą
    2.14
    iz
    2.05
    le
    2.03
    ia
    2.03
    ok
    2.02
    or
    1.94
    ির
    1.94
    og
    1.92
    ó
    1.86
    POSITIVE LOGITS
    R
    1.73
    岖
    1.67
    𝙛
    1.55
    M
    1.49
    P
    1.45
    を追加
    1.38
    𝑬
    1.37
     הייתה
    1.36
     পরই
    1.34
    ⺈
    1.34
    Act Density 0.026%

    No Known Activations