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

    Neuronpedia

    INDEX
    Explanations

    numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лефон
    0.45
    醎
    0.44
    ोटोरोला
    0.43
    💌
    0.43
     satın
    0.42
    飲食店
    0.42
    ोटो
    0.42
    Restaurants
    0.41
    ]}/
    0.41
    ולנד
    0.41
    POSITIVE LOGITS
    $$\
    0.59
     $\
    0.56
     $$\
    0.52
    $\
    0.49
     $
    0.47
     $|
    0.47
     \|
    0.47
     $|\
    0.46
     Q
    0.45
    $
    0.45
    Act Density 0.002%

    No Known Activations