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

    Neuronpedia

    INDEX
    Explanations

    signaling conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )$,
    0.98
     compris
    0.98
    ))
    0.96
     và
    0.88
     ಹಾಗೂ
    0.88
    <unused2152>
    0.87
    ແລະ
    0.86
    ));
    0.86
    こと
    0.86
     pedestrians
    0.85
    POSITIVE LOGITS
    Finally
    1.17
    к
    1.08
     Finally
    1.01
    ان
    0.98
    an
    0.97
    finally
    0.95
     Finalmente
    0.90
    c
    0.86
    あります
    0.84
    lista
    0.84
    Act Density 0.004%

    No Known Activations