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

    Neuronpedia

    INDEX
    Explanations

    g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fuscated
    -0.08
     عدة
    -0.08
     pret
    -0.07
     comprised
    -0.07
    lastic
    -0.07
    derabad
    -0.07
     Spreadsheet
    -0.07
    ぐらい
    -0.07
    accumulator
    -0.07
    -framework
    -0.07
    POSITIVE LOGITS
    cal
    0.07
    康
    0.07
     pilots
    0.07
     Big
    0.07
    ель
    0.07
     Belg
    0.07
    Saint
    0.06
    étique
    0.06
     Wik
    0.06
     getConfig
    0.06
    Act Density 0.001%

    No Known Activations