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

    Neuronpedia

    INDEX
    Explanations

    what kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    you
    0.51
     complemented
    0.43
    れる
    0.41
    라우
    0.40
    леку
    0.40
     می‌دهد
    0.40
    ลอด
    0.40
    Delta
    0.39
     reachable
    0.39
     refracted
    0.39
    POSITIVE LOGITS
    .'”
    0.53
    kj
    0.52
     envío
    0.51
    சொ
    0.50
     Tiến
    0.50
     Estatal
    0.49
    用い
    0.48
     izquier
    0.48
     caballo
    0.47
    ᱝ
    0.47
    Act Density 0.000%

    No Known Activations