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

    Neuronpedia

    INDEX
    Explanations

    introduces new topics or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naquela
    0.79
    Those
    0.75
     Stickers
    0.74
     Those
    0.74
     naquele
    0.71
     aquell
    0.70
    र्टी
    0.69
     Preset
    0.68
     quei
    0.68
    ޙ
    0.68
    POSITIVE LOGITS
     it
    1.45
    它
    1.31
     this
    1.21
     them
    1.11
    它可以
    1.10
     ഇത്
    0.95
     它
    0.94
    这项
    0.94
     these
    0.92
     itp
    0.91
    Act Density 0.603%

    No Known Activations