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

    Neuronpedia

    INDEX
    Explanations

    which is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interestingly
    0.39
    ᐸ
    0.38
    বিষ
    0.38
    其次
    0.37
     seconds
    0.37
     Schools
    0.37
     certainly
    0.37
     earliest
    0.37
     Scholarship
    0.37
    in
    0.36
    POSITIVE LOGITS
     όλα
    0.48
     모든
    0.44
     НЕ
    0.44
     ALL
    0.43
    ۔
    0.43
    ALL
    0.43
    すべての
    0.43
    gue
    0.42
     niemals
    0.42
    ▬▬▬▬
    0.41
    Act Density 0.021%

    No Known Activations