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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    🟦
    1.05
     restful
    1.04
    റു
    1.04
    nehm
    1.00
    த்
    0.99
    gio
    0.96
    ها
    0.96
    ў
    0.96
    รม
    0.95
    نا
    0.95
    POSITIVE LOGITS
    sided
    1.20
     sided
    1.13
     semblance
    1.09
     сталки
    1.07
     sides
    1.04
     yle
    1.04
    レンチ
    1.03
     Ay
    1.03
    indicator
    1.03
    とは思
    1.02
    Act Density 0.000%

    No Known Activations