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

    Neuronpedia

    INDEX
    Explanations

    months following July

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OpenAI
    0.41
     nvidia
    0.40
     SQLAlchemy
    0.38
     MonoBehaviour
    0.38
     softmax
    0.38
     halloween
    0.37
     macOS
    0.37
     thursday
    0.36
     ২০২৩
    0.36
     IPython
    0.36
    POSITIVE LOGITS
     June
    0.91
     August
    0.90
     April
    0.86
     July
    0.85
    June
    0.78
     March
    0.75
    July
    0.75
    April
    0.75
     September
    0.72
     February
    0.71
    Act Density 0.041%

    No Known Activations