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

    Neuronpedia

    INDEX
    Explanations

    determination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     чт
    -0.06
    -0.06
     guidelines
    -0.06
    	rb
    -0.06
    -0.06
    Voltage
    -0.06
     Colt
    -0.06
     grams
    -0.05
     loan
    -0.05
    Services
    -0.05
    POSITIVE LOGITS
    acidad
    0.07
     úspě
    0.07
     жінок
    0.07
     adjusts
    0.07
    чески
    0.07
     갈
    0.06
    EXPR
    0.06
     Macy
    0.06
     dưới
    0.06
    ест
    0.06
    Act Density 0.053%

    No Known Activations