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

    Neuronpedia

    INDEX
    Explanations

    square engine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.33
     नेहमी
    0.33
    .
    0.33
     சா
    0.32
     சிறப்பாக
    0.32
     परंतु
    0.31
    Although
    0.30
     แต่
    0.30
     ப
    0.30
     புதிய
    0.30
    POSITIVE LOGITS
     finans
    0.46
     CEOs
    0.42
     arrog
    0.41
    why
    0.41
     финанси
    0.41
    bankruptcy
    0.41
     financi
    0.40
     financials
    0.40
    fraud
    0.40
     immoral
    0.39
    Act Density 0.000%

    No Known Activations