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

    Neuronpedia

    INDEX
    Explanations

    tracking and deployment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    梗
    0.41
     delf
    0.40
    𝗚
    0.40
     Computational
    0.40
     Bioinformatics
    0.40
     Karth
    0.40
     लिस्ट
    0.39
    ણામ
    0.38
    𝗨
    0.38
     DP
    0.38
    POSITIVE LOGITS
     wand
    0.81
    wand
    0.77
     Wand
    0.73
     wandering
    0.72
     wandered
    0.65
     wander
    0.63
     wanders
    0.63
     mlflow
    0.57
    tracking
    0.55
     Wander
    0.54
    Act Density 0.018%

    No Known Activations