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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    heet
    -0.07
     marches
    -0.06
    กราคม
    -0.06
     Ey
    -0.06
     saves
    -0.06
    ,False
    -0.06
    .SimpleDateFormat
    -0.06
    دواج
    -0.06
    DAY
    -0.06
     illustrations
    -0.06
    POSITIVE LOGITS
     ako
    0.07
    agoon
    0.07
    メント
    0.06
     Kö
    0.06
    .</
    0.06
    空间
    0.06
     businessman
    0.06
     savedInstanceState
    0.06
    Variables
    0.06
    oods
    0.06
    Act Density 0.003%

    No Known Activations