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

    Neuronpedia

    INDEX
    Explanations

    Lack of knowledge/awareness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Food
    -0.07
     Configuration
    -0.07
    _keep
    -0.06
     Newtown
    -0.06
     food
    -0.06
     Dive
    -0.06
     Guinness
    -0.06
    .fits
    -0.06
     بازیگر
    -0.06
     Concrete
    -0.06
    POSITIVE LOGITS
    ANTED
    0.07
    ITIZE
    0.07
    	block
    0.07
     marsh
    0.07
     ymax
    0.06
     assortment
    0.06
     můžete
    0.06
    ment
    0.06
     normal
    0.06
     sey
    0.06
    Act Density 0.127%

    No Known Activations