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

    Neuronpedia

    INDEX
    Explanations

    transportation and movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estatura
    0.47
     ٹیم
    0.45
     직접
    0.44
     تعالی
    0.44
    暐
    0.43
     امریکی
    0.43
     সরাস
    0.43
     تعلیم
    0.43
    อังกฤษ
    0.43
     êtres
    0.42
    POSITIVE LOGITS
     with
    0.49
    w
    0.47
     from
    0.45
    ↵↵
    0.45
     that
    0.43
    load
    0.42
     Power
    0.42
     &
    0.42
     xwe
    0.41
     svojim
    0.40
    Act Density 0.003%

    No Known Activations