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

    Neuronpedia

    INDEX
    Explanations

    announced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Civil
    -0.07
    Locations
    -0.07
     Migration
    -0.07
     Lub
    -0.07
    抜
    -0.07
     NUM
    -0.06
     bóng
    -0.06
     �
    -0.06
    /resource
    -0.06
     Od
    -0.06
    POSITIVE LOGITS
    \uff
    0.08
     Sherman
    0.06
     remembering
    0.06
    Experiment
    0.06
    	className
    0.06
    ‌کنند
    0.06
    탁
    0.06
    unittest
    0.06
     furnace
    0.05
     announces
    0.05
    Act Density 0.025%

    No Known Activations