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

    Neuronpedia

    INDEX
    Explanations

    style, pattern, finish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sản
    0.74
    Với
    0.71
     Mỹ
    0.70
     Với
    0.69
     Crater
    0.69
     Moż
    0.68
    ꒦
    0.68
     Bước
    0.68
     Bạn
    0.68
     Dalam
    0.67
    POSITIVE LOGITS
     conversely
    0.64
     suspended
    0.59
    0.58
     cut
    0.57
     media
    0.57
     said
    0.56
     resigned
    0.56
     city
    0.56
     b
    0.55
     doping
    0.55
    Act Density 0.001%

    No Known Activations