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

    Neuronpedia

    INDEX
    Explanations

    depends on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Abhäng
    1.03
    around
    0.93
    Around
    0.93
     dependence
    0.89
     around
    0.88
     rely
    0.86
     reliance
    0.84
     off
    0.81
     relying
    0.79
     Around
    0.78
    POSITIVE LOGITS
    SIZ
    0.82
     જેના
    0.76
    <unused606>
    0.75
    PIPE
    0.72
    ખી
    0.70
     ভুল
    0.70
    UMO
    0.69
     মিজান
    0.69
    endio
    0.68
    ાં
    0.67
    Act Density 0.047%

    No Known Activations