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

    Neuronpedia

    INDEX
    Explanations

    categorized for clarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desirable
    0.40
    FERRED
    0.37
    悟空
    0.36
    டக
    0.36
     simplifies
    0.35
     siguiendo
    0.34
     Simplified
    0.34
     suficient
    0.33
     Rel
    0.33
     Simple
    0.33
    POSITIVE LOGITS
     reference
    0.98
    reference
    0.91
     context
    0.82
    参考
    0.82
     clarity
    0.82
     Reference
    0.80
    Reference
    0.76
     REFERENCE
    0.75
     참고
    0.73
     referência
    0.71
    Act Density 0.043%

    No Known Activations