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

    Neuronpedia

    INDEX
    Explanations

    not alone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    geoning
    0.53
     problemat
    0.49
     predominate
    0.48
     দিতেন
    0.45
     ہوسک
    0.44
    豈
    0.44
     선보
    0.43
     सकेगा
    0.43
     থাকতেন
    0.42
     மேற்கொள்ள
    0.42
    POSITIVE LOGITS
    <unused2172>
    0.47
    <unused2125>
    0.45
    
    0.45
     VERY
    0.45
     absolutely
    0.44
     ‍
    0.43
    0.43
    alya
    0.42
     magnetometer
    0.41
    閬
    0.41
    Act Density 0.019%

    No Known Activations