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

    Neuronpedia

    INDEX
    Explanations

    our team

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ار
    1.63
    ा
    1.53
    ins
    1.52
    ไม่
    1.51
    Z
    1.49
    s
    1.46
    もちろん
    1.42
     Lordships
    1.38
     propio
    1.34
     erstes
    1.34
    POSITIVE LOGITS
    та
    1.95
    ни
    1.49
    те
    1.48
    𝘵
    1.43
    ა
    1.41
    ти
    1.38
     способы
    1.38
     раза
    1.37
    т
    1.37
    ้
    1.32
    Act Density 0.086%

    No Known Activations