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

    Neuronpedia

    INDEX
    Explanations

    reverse or reversed order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एकमात्र
    0.44
     तोला
    0.43
     линей
    0.42
    izedBox
    0.41
    emeinschaft
    0.40
     지속
    0.39
     totalidad
    0.39
     සම
    0.39
     perpetuity
    0.38
     potrebbero
    0.38
    POSITIVE LOGITS
    reverse
    0.69
     reversed
    0.66
     먼저
    0.66
    reversed
    0.66
     reverse
    0.65
     zuerst
    0.64
     Reverse
    0.59
    Reverse
    0.58
     Reversed
    0.58
     reverses
    0.56
    Act Density 0.149%

    No Known Activations