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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    к
    1.14
    将
    1.13
    在
    1.10
    el
    1.06
    가를
    1.02
    在這個
    1.02
    被
    1.01
    也是
    0.97
    涅
    0.96
    指
    0.96
    POSITIVE LOGITS
    𝐫
    1.37
    𝐚
    1.32
    ت
    1.26
    𝗮
    1.26
    ه‌های
    1.25
    uomo
    1.25
     වන
    1.24
    즌
    1.24
    1.17
    tournament
    1.17
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.