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

    Neuronpedia

    INDEX
    Explanations

    sentence corrections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multi
    0.77
     data
    0.74
     internal
    0.72
     நிற்கும்
    0.70
     evolving
    0.70
     generating
    0.69
     approx
    0.69
     binnen
    0.68
     &
    0.68
     intra
    0.68
    POSITIVE LOGITS
     фрук
    0.89
    例文帳に追加
    0.82
     ँ
    0.80
     turistas
    0.79
    ＿＿
    0.78
    myapplication
    0.77
    akespeare
    0.77
    orestation
    0.77
     indexRouter
    0.77
     Tourists
    0.76
    Act Density 0.770%

    No Known Activations