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

    Neuronpedia

    INDEX
    Explanations

    see how or view through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.13
    as
    0.91
     benessere
    0.90
     emberek
    0.89
     universitario
    0.89
     aziende
    0.89
    িগ্ন
    0.88
    east
    0.88
    hotels
    0.87
    اهرين
    0.86
    POSITIVE LOGITS
    本次
    0.90
    ון
    0.81
     pinpoint
    0.80
    性和
    0.79
     absc
    0.79
    该
    0.75
    ър
    0.73
    ともに
    0.73
     bodied
    0.73
    踌
    0.73
    Act Density 0.211%

    No Known Activations