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

    Neuronpedia

    INDEX
    Explanations

    involved in or related to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    كي
    0.42
    ется
    0.39
     اين
    0.37
     فيلم
    0.37
     يا
    0.35
     مي
    0.34
    üp
    0.34
     ي
    0.34
     суд
    0.34
     Și
    0.34
    POSITIVE LOGITS
    at
    0.47
    p
    0.45
    u
    0.42
    ल
    0.41
    z
    0.40
    त
    0.39
    et
    0.38
    al
    0.38
     with
    0.38
    t
    0.37
    Act Density 0.590%

    No Known Activations