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

    Neuronpedia

    INDEX
    Explanations

    once information is provided

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    രും
    0.90
    ขณะ
    0.90
    transparent
    0.89
     transparent
    0.89
    舘
    0.88
    ნობ
    0.88
     bros
    0.88
     våra
    0.85
     nuestras
    0.85
    媒体
    0.85
    POSITIVE LOGITS
     Montgomery
    1.08
    Montgomery
    1.04
     Crimes
    1.02
     manslaughter
    1.02
    ilgan
    1.01
     Finley
    1.00
     همراه
    0.99
    衣裙
    0.98
     misdemeanor
    0.97
     Lei
    0.96
    Act Density 0.191%

    No Known Activations