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

    Neuronpedia

    INDEX
    Explanations

    Declaration of Independence quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     завтра
    -0.07
     dens
    -0.06
    ереж
    -0.06
    owie
    -0.06
    �이
    -0.06
     prostřed
    -0.06
    яд
    -0.06
    	Write
    -0.06
     wir
    -0.06
     Winner
    -0.06
    POSITIVE LOGITS
     ApplicationController
    0.07
     NGX
    0.07
    _APPS
    0.07
    .AUTH
    0.07
     contracted
    0.07
    salt
    0.07
     cinnamon
    0.06
    _PARENT
    0.06
     setEmail
    0.06
     '.')
    0.06
    Act Density 0.007%

    No Known Activations