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

    Neuronpedia

    INDEX
    Explanations

    introducing an explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     predefined
    0.38
     также
    0.37
     Ayrıca
    0.36
    த்திலும்
    0.35
     તેમજ
    0.35
     також
    0.34
    ),
    0.33
     ulteriori
    0.33
     tels
    0.33
    ²,
    0.33
    POSITIVE LOGITS
    那就是
    0.51
    竟然
    0.47
     namelijk
    0.44
    したのは
    0.44
    居然
    0.43
     nämlich
    0.42
    的是
    0.42
     bahwa
    0.41
     totiž
    0.40
     rằng
    0.39
    Act Density 0.232%

    No Known Activations