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

    Neuronpedia

    INDEX
    Explanations

    cleaning, washing, and rinsing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cryptography
    0.90
     информационной
    0.86
     podpis
    0.85
    交易
    0.84
    aliana
    0.83
     HSPB
    0.82
    サーバ
    0.82
     puisi
    0.81
    uatu
    0.80
    ujudkan
    0.80
    POSITIVE LOGITS
     rinsing
    2.48
     cleaning
    2.30
     scrubbing
    2.24
     washing
    2.16
     wiping
    2.13
     cleansing
    2.13
     rinsed
    2.02
     rinse
    2.02
     wash
    2.00
     Cleaning
    1.99
    Act Density 0.260%

    No Known Activations