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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     社
    0.46
     ಉತ್ತ
    0.45
    ейчас
    0.43
    atthena
    0.43
    ವಾಡ
    0.42
     Masyarakat
    0.42
     \\\
    0.41
    ระยะ
    0.41
    FileName
    0.40
    mlabeledtr
    0.40
    POSITIVE LOGITS
    B
    0.49
    King
    0.47
    According
    0.46
    що
    0.45
    Water
    0.44
    Ur
    0.43
     que
    0.43
     dois
    0.43
    ு
    0.43
    Think
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.