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

    Neuronpedia

    INDEX
    Explanations

    Instructions and questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    restaurant
    -0.07
    _prices
    -0.06
    threshold
    -0.06
     PREFIX
    -0.06
    _routing
    -0.06
     femin
    -0.06
    	instance
    -0.06
     Hell
    -0.06
    -error
    -0.06
    官
    -0.06
    POSITIVE LOGITS
     ابراه
    0.07
     HV
    0.06
     سنة
    0.06
    kee
    0.06
    蘭
    0.06
    ंय
    0.06
     honestly
    0.06
    Actualizar
    0.06
     __
    0.06
     irresist
    0.06
    Act Density 0.058%

    No Known Activations