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

    Neuronpedia

    INDEX
    Explanations

    ```python definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     print
    0.74
     else
    0.71
     then
    0.70
     exit
    0.64
     shirt
    0.63
     while
    0.62
    print
    0.60
     Print
    0.60
    export
    0.60
    exit
    0.59
    POSITIVE LOGITS
     básicamente
    1.02
     essentiellement
    0.92
     везде
    0.92
    "..
    0.91
     ..$
    0.88
     موارد
    0.87
     paradigms
    0.86
    acije
    0.86
     presupp
    0.85
    രിക
    0.84
    Act Density 0.139%

    No Known Activations