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

    Neuronpedia

    INDEX
    Explanations

    commute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ير
    0.79
    لا
    0.77
    ס
    0.76
    لع
    0.73
    رة
    0.70
    ق
    0.68
    اد
    0.68
    دار
    0.67
    ро
    0.66
    رت
    0.66
    POSITIVE LOGITS
     commute
    1.41
     commuters
    1.18
     commuting
    1.14
     commutes
    1.10
     commuter
    0.90
     да
    0.81
     通勤
    0.80
    通勤
    0.78
    commuting
    0.76
     hours
    0.71
    Act Density 0.005%

    No Known Activations