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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	as
    -0.07
     INTO
    -0.07
     as
    -0.07
     Tas
    -0.06
    ятия
    -0.06
    anych
    -0.06
     بنابراین
    -0.06
    ประกาศ
    -0.06
     ters
    -0.06
    на
    -0.06
    POSITIVE LOGITS
     while
    0.11
     whilst
    0.09
     WHILE
    0.08
     mientras
    0.08
    .Rel
    0.07
    while
    0.07
    `;↵
    0.07
    _while
    0.07
     шп
    0.07
    )");
↵
    0.07
    Act Density 0.030%

    No Known Activations