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

    Neuronpedia

    INDEX
    Explanations

    offering further suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     νέ
    0.97
     És
    0.78
    ğu
    0.77
    âce
    0.76
    ين
    0.76
    IMPLEMENT
    0.74
    ísmo
    0.72
    なる
    0.71
     savaş
    0.71
     révèle
    0.71
    POSITIVE LOGITS
    ४
    0.76
     been
    0.71
    8
    0.71
    त
    0.70
    ী
    0.68
    ৪
    0.68
    ৯
    0.68
     modifications
    0.67
     vases
    0.66
    in
    0.65
    Act Density 0.046%

    No Known Activations