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

    Neuronpedia

    INDEX
    Explanations

    waste disposal and management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recycling
    1.21
     Recycling
    1.15
     recycle
    1.06
     Recycle
    1.00
     recicl
    0.99
    回收
    0.95
     recycled
    0.95
     recycler
    0.92
    recycl
    0.88
    recycle
    0.86
    POSITIVE LOGITS
     contaminated
    0.55
    infected
    0.54
     Infected
    0.50
     infected
    0.49
    mixed
    0.47
    contaminated
    0.46
    generated
    0.43
     tainted
    0.43
     compressible
    0.43
    encrypted
    0.42
    Act Density 0.016%

    No Known Activations