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

    Neuronpedia

    INDEX
    Explanations

    deployment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ул
    0.52
     daqu
    0.50
    ОВ
    0.49
    improvements
    0.47
    ఆ
    0.47
    confusion
    0.47
    curvature
    0.46
    clamps
    0.46
    णाम
    0.46
    笏
    0.46
    POSITIVE LOGITS
     ubiqu
    0.48
     deployment
    0.44
     deployed
    0.44
     bucket
    0.43
     TCP
    0.43
     knows
    0.43
     waved
    0.42
     middle
    0.41
     deploy
    0.41
     redeem
    0.40
    Act Density 0.009%

    No Known Activations