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

    Neuronpedia

    INDEX
    Explanations

    sharing, URL, server

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ito
    0.46
    órm
    0.44
    ó
    0.44
     к
    0.42
     п
    0.41
     Quando
    0.41
    ú
    0.41
     ró
    0.40
    x
    0.40
     pewter
    0.39
    POSITIVE LOGITS
    ⚠
    0.46
     aeron
    0.45
     shareholders
    0.44
     lähe
    0.44
    Viki
    0.43
    Biographie
    0.42
    Vaterpolo
    0.42
     patrimoine
    0.42
    服务器
    0.40
     장애
    0.40
    Act Density 0.002%

    No Known Activations