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

    Neuronpedia

    INDEX
    Explanations

    mansions/houses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kazy
    -0.07
     ultra
    -0.07
    [counter
    -0.07
    092
    -0.06
     cracking
    -0.06
    фік
    -0.06
    -changing
    -0.06
     guards
    -0.06
    ाऊ
    -0.06
     cultivate
    -0.06
    POSITIVE LOGITS
    Songs
    0.07
     класс
    0.07
    .’
    0.07
     iş
    0.07
     Irvine
    0.06
    .ico
    0.06
     negot
    0.06
    *B
    0.06
     زم
    0.06
    	tab
    0.06
    Act Density 0.011%

    No Known Activations