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

    Neuronpedia

    INDEX
    Explanations

    right-to-left text direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +")
    0.45
     +'
    0.45
     +"
    0.42
     $+$
    0.41
     underage
    0.41
    :"+
    0.39
     cheaply
    0.39
    ชน์
    0.39
    +","+
    0.39
     "+"
    0.39
    POSITIVE LOGITS
     RTL
    0.97
     Right
    0.92
    Right
    0.91
     Direction
    0.89
     right
    0.87
     direction
    0.85
    Direction
    0.84
    direction
    0.82
    right
    0.81
     오른쪽
    0.81
    Act Density 0.012%

    No Known Activations