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

    Neuronpedia

    INDEX
    Explanations

    level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getWidth
    -0.06
     sayı
    -0.06
     kir
    -0.06
     bureauc
    -0.06
    ictionaries
    -0.06
     españ
    -0.06
    .access
    -0.06
    keit
    -0.06
     apare
    -0.06
     موجب
    -0.06
    POSITIVE LOGITS
    appropri
    0.07
    ropical
    0.07
     мол
    0.07
     شهر
    0.07
    =>
    0.06
     refrigerator
    0.06
    brook
    0.06
    ilege
    0.06
     gall
    0.06
     workload
    0.06
    Act Density 0.001%

    No Known Activations