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

    Neuronpedia

    INDEX
    Explanations

    retailer and manufacturer emails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    キシ
    0.46
    ाने
    0.46
    క్సి
    0.43
     palud
    0.42
    之前
    0.41
    వరకు
    0.40
    A
    0.40
    ifiers
    0.40
    నిక
    0.39
     idealistic
    0.39
    POSITIVE LOGITS
     ně
    0.48
    deux
    0.46
     podľa
    0.46
    َم
    0.46
    your
    0.46
     volgens
    0.45
    according
    0.45
     wiecz
    0.44
    ܀
    0.43
     Това
    0.42
    Act Density 0.001%

    No Known Activations