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

    Neuronpedia

    INDEX
    Explanations

    Code/Exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zám
    -0.06
     bc
    -0.06
     sailors
    -0.06
    (radius
    -0.06
    endar
    -0.06
     меч
    -0.06
     належ
    -0.06
    Dual
    -0.06
    .Utility
    -0.06
     Arn
    -0.05
    POSITIVE LOGITS
     dealt
    0.07
     том
    0.07
    	delete
    0.07
     паль
    0.06
     patients
    0.06
    	constructor
    0.06
     cere
    0.06
    	Editor
    0.06
     fruit
    0.06
    )}
    0.06
    Act Density 0.000%

    No Known Activations