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

    Neuronpedia

    INDEX
    Explanations

    gentle sensory descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وبالتالي
    0.98
     tzv
    0.97
     verwenden
    0.94
     많이
    0.91
    めっちゃ
    0.91
     usar
    0.90
     realizar
    0.89
     menggunakan
    0.88
    Basically
    0.88
    siehe
    0.87
    POSITIVE LOGITS
     etched
    1.10
     shimmer
    0.97
     shimmering
    0.95
     pulsing
    0.95
     bathed
    0.94
     woven
    0.94
     beneath
    0.93
     kissed
    0.91
     threaded
    0.90
     draped
    0.89
    Act Density 1.316%

    No Known Activations