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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     امکان
    -0.07
     موجب
    -0.07
     가족
    -0.06
    _scripts
    -0.06
     appName
    -0.06
     سلام
    -0.06
    .Day
    -0.06
     Ibrahim
    -0.06
     folder
    -0.06
    stre
    -0.06
    POSITIVE LOGITS
     cosmetics
    0.07
    _im
    0.06
    лося
    0.06
    ект
    0.06
     */↵
    0.06
    IRST
    0.06
    、↵↵
    0.06
     INPUT
    0.06
    ентом
    0.06
     DISTRIBUT
    0.06
    Act Density 0.010%

    No Known Activations