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

    Neuronpedia

    INDEX
    Explanations

    say hyphen

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ი
    0.43
    एसआय
    0.40
     परिवेश
    0.39
     Го
    0.37
     Traditionally
    0.37
     URLs
    0.37
    Вы
    0.37
     Rankings
    0.37
     About
    0.36
     Around
    0.36
    POSITIVE LOGITS
     buttery
    0.39
    কৃ
    0.38
    第九
    0.38
    תי
    0.38
     दूध
    0.38
    電子
    0.37
    mbr
    0.37
    اتے
    0.36
     munc
    0.36
    9
    0.36
    Act Density 0.000%

    No Known Activations