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

    Neuronpedia

    INDEX
    Explanations

    user context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     continuamos
    0.47
    otopic
    0.45
     sogenannten
    0.44
     전달
    0.44
     luminance
    0.43
    增加
    0.42
    ామ
    0.42
    Pren
    0.41
     mecanismos
    0.41
     cyclic
    0.41
    POSITIVE LOGITS
     bạn
    0.82
     tendrás
    0.80
     youll
    0.79
     você
    0.77
    你会
    0.74
    你會
    0.73
     you
    0.73
    你要
    0.70
     будете
    0.70
     आपको
    0.69
    Act Density 0.132%

    No Known Activations