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

    Neuronpedia

    INDEX
    Explanations

    character, debtor, surprise, connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zelfde
    0.42
    }}_{
    0.42
     ಸ್ಥಾನ
    0.42
     ನಮ್ಮ
    0.42
     நவ
    0.41
    yatiti
    0.41
    наў
    0.40
     ಅಥವಾ
    0.40
    場合は
    0.39
    chest
    0.39
    POSITIVE LOGITS
     and
    0.52
     partly
    0.49
     uses
    0.46
    XE
    0.42
    5
    0.41
    4
    0.41
    8
    0.41
     engages
    0.41
    3
    0.41
     overcomes
    0.39
    Act Density 0.008%

    No Known Activations