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

    Neuronpedia

    INDEX
    Explanations

    international code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    专项
    0.67
    êter
    0.67
     bú
    0.65
    だったら
    0.65
     off
    0.61
     उदा
    0.61
     Off
    0.61
     붙
    0.60
     $=$
    0.60
     afară
    0.60
    POSITIVE LOGITS
    Qi
    0.72
    Quantum
    0.70
    QN
    0.68
     المخت
    0.67
     स्वतंत्रता
    0.64
     metastability
    0.64
    pure
    0.64
    Capability
    0.63
     магазин
    0.62
     Quantum
    0.62
    Act Density 0.024%

    No Known Activations