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

    Neuronpedia

    INDEX
    Explanations

    entering gravity or program information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ایسے
    0.76
    vart
    0.75
    Quite
    0.74
     ಸೂ
    0.74
    Designed
    0.73
    的他
    0.72
    Références
    0.72
     miejsc
    0.72
    য়ী
    0.71
     چھوٹے
    0.70
    POSITIVE LOGITS
     CRISPR
    0.86
     Numpy
    0.78
     graphene
    0.78
     있지만
    0.77
     TPS
    0.76
     Linux
    0.76
     LaTeX
    0.75
     미래
    0.75
     ind
    0.74
     OpenAI
    0.74
    Act Density 0.001%

    No Known Activations