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

    Neuronpedia

    INDEX
    Explanations

    sci-fi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oul
    0.40
    microseconds
    0.40
     වශ
    0.39
     गांठ
    0.37
     гру
    0.37
    ysin
    0.37
    ogg
    0.36
    äle
    0.36
     Европе
    0.36
     सामील
    0.36
    POSITIVE LOGITS
     sci
    0.98
     Sci
    0.97
    Sci
    0.86
     fi
    0.71
     SCI
    0.68
    sci
    0.65
     Fi
    0.63
    Fi
    0.62
     scientifically
    0.61
     Scientific
    0.61
    Act Density 0.004%

    No Known Activations