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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ẵn
    0.41
    与
    0.40
     शुक्रवार
    0.40
     两
    0.40
     Vox
    0.38
     बुधवार
    0.38
     Украины
    0.37
    ᖓ
    0.37
    学会
    0.37
    㘟
    0.37
    POSITIVE LOGITS
    нь
    0.52
     Ц
    0.48
    ань
    0.43
    Ци
    0.42
     ци
    0.42
    Ц
    0.41
     Ци
    0.41
    нями
    0.40
    ŏ
    0.40
    tsz
    0.39
    Act Density 0.004%

    No Known Activations