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

    Neuronpedia

    INDEX
    Explanations

    while loop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InteropServices
    0.35
    ifères
    0.35
    ťou
    0.34
     Corse
    0.34
    ടതി
    0.34
     alen
    0.34
    Für
    0.33
    对于
    0.33
     Lightweight
    0.33
     সেজন্য
    0.33
    POSITIVE LOGITS
     while
    2.44
    while
    2.44
     mientras
    2.14
     enquanto
    2.06
     WHILE
    2.06
     mentre
    1.95
     While
    1.94
    While
    1.89
     whilst
    1.81
     terwijl
    1.80
    Act Density 0.045%

    No Known Activations