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

    Neuronpedia

    INDEX
    Explanations

    141

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IGH
    -0.07
     /.
    -0.07
     pois
    -0.07
    оратив
    -0.06
     Penalty
    -0.06
    uku
    -0.06
    akov
    -0.06
    angled
    -0.06
    \modules
    -0.06
    ков
    -0.06
    POSITIVE LOGITS
    	lua
    0.08
     Appears
    0.07
    ْد
    0.07
     RAF
    0.07
     locationManager
    0.07
     بهتر
    0.07
    Applied
    0.07
     Applied
    0.06
     thuốc
    0.06
     fiyat
    0.06
    Act Density 0.003%

    No Known Activations