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

    Neuronpedia

    INDEX
    Explanations

    password

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XB
    -0.07
     bacon
    -0.07
    309
    -0.06
    лой
    -0.06
     bmp
    -0.06
     pobl
    -0.06
    不会
    -0.06
     đại
    -0.06
    locate
    -0.06
    does
    -0.06
    POSITIVE LOGITS
     Setup
    0.07
     pathology
    0.06
     SPA
    0.06
    	wp
    0.06
     reconc
    0.06
     Regina
    0.06
    .HandleFunc
    0.06
    	Camera
    0.06
     passwd
    0.06
    	Dictionary
    0.06
    Act Density 0.007%

    No Known Activations