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

    Neuronpedia

    INDEX
    Explanations

    population

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .EN
    -0.07
     tung
    -0.06
     Wing
    -0.06
    bě
    -0.06
    程序
    -0.06
    ω
    -0.06
    ोव
    -0.06
    iд
    -0.06
     fashioned
    -0.06
    _setup
    -0.06
    POSITIVE LOGITS
     teasing
    0.07
    Trait
    0.06
     dissect
    0.06
     appealing
    0.06
     battled
    0.06
    -split
    0.06
     نتیجه
    0.06
     battling
    0.06
     accompanies
    0.06
    ossible
    0.06
    Act Density 0.025%

    No Known Activations