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

    Neuronpedia

    INDEX
    Explanations

    learning and living

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ट
    1.37
    स
    1.23
    िंग
    1.18
     contending
    1.17
     transfected
    1.17
    ot
    1.14
    ️
    1.14
     holdings
    1.14
     lingering
    1.14
    ingly
    1.11
    POSITIVE LOGITS
    ための
    1.30
    ्ज
    1.15
     puno
    0.95
    ্লাহ
    0.94
    دد
    0.93
    場合の
    0.92
    шее
    0.90
    د
    0.90
    hasta
    0.88
     porcent
    0.88
    Act Density 0.308%

    No Known Activations