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

    Neuronpedia

    INDEX
    Explanations

    end of the world predictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الدولي
    -0.07
     inve
    -0.07
     території
    -0.07
    iglia
    -0.06
    igg
    -0.06
     Datos
    -0.06
     mạnh
    -0.06
    ARING
    -0.06
     Swords
    -0.06
    Months
    -0.06
    POSITIVE LOGITS
    .Design
    0.07
     solder
    0.07
     escri
    0.07
    ighest
    0.07
     compiler
    0.07
    .now
    0.06
    ¯¯¯¯
    0.06
    .double
    0.06
     上涨
    0.06
    风
    0.06
    Act Density 0.013%

    No Known Activations