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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /
    -0.07
     lenses
    -0.07
     =
    -0.07
     Kawasaki
    -0.06
    uries
    -0.06
     суду
    -0.06
    	ap
    -0.06
     conspir
    -0.06
     cylinders
    -0.06
     females
    -0.06
    POSITIVE LOGITS
    Had
    0.07
    Must
    0.06
     xét
    0.06
    Facade
    0.06
     درد
    0.06
     MMI
    0.06
     trope
    0.06
     contrad
    0.06
    DebugEnabled
    0.06
    icros
    0.06
    Act Density 0.016%

    No Known Activations