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

    Neuronpedia

    INDEX
    Explanations

    analysis and deconstruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ногие
    0.43
    ються
    0.42
    皞
    0.42
    Pieces
    0.41
    Rocks
    0.41
    calup
    0.41
     banyaknya
    0.41
    Khi
    0.40
    あります
    0.40
     বছর
    0.39
    POSITIVE LOGITS
     affliction
    0.46
     revive
    0.43
     \%
    0.43
     문제를
    0.40
     Ell
    0.40
     laptop
    0.39
     효과
    0.39
     금
    0.39
     미
    0.38
    无可
    0.38
    Act Density 0.000%

    No Known Activations