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

    Neuronpedia

    INDEX
    Explanations

    Less than sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     predictor
    -0.06
    	tc
    -0.06
     привед
    -0.06
     mommy
    -0.06
     centroids
    -0.06
     sack
    -0.06
     withhold
    -0.06
     amused
    -0.06
    Implicit
    -0.06
    struct
    -0.06
    POSITIVE LOGITS
     civilizations
    0.07
    —for
    0.07
    ATION
    0.07
     appropriations
    0.07
    emergency
    0.06
     remodel
    0.06
     unlocking
    0.06
     freelancer
    0.06
     emergencies
    0.06
     『
    0.06
    Act Density 0.012%

    No Known Activations