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

    Neuronpedia

    INDEX
    Explanations

    identifying specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     செய்க
    0.47
     местах
    0.46
    seats
    0.45
     הת
    0.44
     அளவிற்கு
    0.44
     Kentucky
    0.43
     Supportive
    0.43
     መ
    0.42
     दश
    0.42
     CIRCU
    0.42
    POSITIVE LOGITS
    اي
    0.47
    a
    0.45
    الا
    0.44
    你需要
    0.43
    proc
    0.41
    BatchNorm
    0.41
    鿁
    0.40
     relevancia
    0.40
    اح
    0.39
    alang
    0.39
    Act Density 0.011%

    No Known Activations