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

    Neuronpedia

    INDEX
    Explanations

    like-new condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ری
    0.84
    ೊಳ್ಳ
    0.79
    า
    0.74
    ने
    0.73
     Möglich
    0.69
    ή
    0.68
    是我们
    0.68
     MATERIALS
    0.67
    हारिक
    0.66
    larına
    0.65
    POSITIVE LOGITS
     disparu
    0.77
    MAE
    0.76
    دين
    0.75
    د
    0.75
    0
    0.74
     deftly
    0.73
     recib
    0.71
    ARE
    0.71
     blanche
    0.70
     *
    0.69
    Act Density 0.000%

    No Known Activations