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

    Neuronpedia

    INDEX
    Explanations

    code loops with int or let

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Range
    0.96
     Range
    0.95
     range
    0.90
     ধরিয়
    0.88
     discretization
    0.85
     indeks
    0.83
    êmement
    0.83
    ците
    0.83
    Enumerator
    0.83
    ธ์
    0.82
    POSITIVE LOGITS
    ;;
    1.02
    ;;)
    0.96
     ;;
    0.86
    ###
    0.78
     ;
    0.75
    auto
    0.74
    ##
    0.73
    edit
    0.73
    ；
    0.72
    var
    0.72
    Act Density 0.030%

    No Known Activations