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

    Neuronpedia

    INDEX
    Explanations

    digit by digit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snee
    0.42
    czek
    0.41
     Foods
    0.41
    France
    0.41
    Richmond
    0.40
    धिकरण
    0.40
     вме
    0.39
    Foods
    0.39
     Richmond
    0.39
    প্তর
    0.39
    POSITIVE LOGITS
     digit
    2.00
     digits
    2.00
    Digits
    1.82
    digits
    1.80
    digit
    1.77
    Digit
    1.77
     dígitos
    1.68
     Digit
    1.67
     díg
    1.56
     डिजिट
    1.39
    Act Density 0.048%

    No Known Activations