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

    Neuronpedia

    INDEX
    Explanations

    whether or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Analysis
    0.37
    Ol
    0.35
    MDEw
    0.35
     고려
    0.34
     Whatever
    0.34
    Altri
    0.33
    explanation
    0.33
    Whatever
    0.33
     schönen
    0.33
    Tìm
    0.33
    POSITIVE LOGITS
     whether
    0.82
    whether
    0.73
    是否
    0.72
     apakah
    0.64
     Whether
    0.61
     WHETHER
    0.59
    是否有
    0.59
     是否
    0.57
     cuándo
    0.57
    Whether
    0.57
    Act Density 0.617%

    No Known Activations