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

    Neuronpedia

    INDEX
    Explanations

    urls with paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     idiots
    0.41
     Games
    0.39
     odds
    0.38
     Rennen
    0.38
    :"))
    0.38
     Odds
    0.37
    不由
    0.36
     species
    0.36
     Rept
    0.36
     deduced
    0.35
    POSITIVE LOGITS
    /)
    0.45
    по
    0.43
    which
    0.40
    г
    0.40
    /.
    0.40
    ін
    0.40
    matrix
    0.38
    ка
    0.38
    ্স
    0.38
    /?
    0.38
    Act Density 0.027%

    No Known Activations