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

    Neuronpedia

    INDEX
    Explanations

    CIFAR-10 dataset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vot
    0.72
     sauvegard
    0.71
     seguros
    0.70
     custos
    0.69
     cork
    0.68
     abbrevi
    0.68
     antip
    0.65
    fores
    0.65
     argv
    0.63
    :‏
    0.63
    POSITIVE LOGITS
    이
    1.06
    また
    0.88
    ين
    0.87
    چه
    0.86
    人在
    0.76
    executor
    0.72
    其他
    0.72
     quét
    0.71
    ியான
    0.71
    ت
    0.70
    Act Density 0.001%

    No Known Activations