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

    Neuronpedia

    INDEX
    Explanations

    the first or only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     likes
    0.72
     ignorance
    0.70
     a
    0.70
     an
    0.67
     myopia
    0.66
     nedir
    0.65
     beautiful
    0.64
     simply
    0.64
    是多少
    0.63
     Likes
    0.62
    POSITIVE LOGITS
     الذي
    0.93
     التي
    0.92
     التى
    0.90
     contender
    0.83
     ಕಾರಣ
    0.80
     членом
    0.79
    ที่
    0.78
    ที่จะ
    0.76
     που
    0.75
    whose
    0.74
    Act Density 0.004%

    No Known Activations