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

    Neuronpedia

    INDEX
    Explanations

    waste composition management sorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    噙
    0.52
    reflectionMap
    0.49
     নিউইয়
    0.45
    纽约
    0.45
    ىر
    0.45
    交给
    0.45
    林的
    0.45
    ాలతో
    0.44
    ించాలి
    0.44
    指令
    0.43
    POSITIVE LOGITS
    s
    0.58
    n
    0.54
    0.52
    t
    0.50
    m
    0.46
    d
    0.46
    sides
    0.46
            
    0.46
     started
    0.46
     heter
    0.45
    Act Density 0.002%

    No Known Activations