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

    Neuronpedia

    INDEX
    Explanations

    Hello

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Наз
    -0.07
     abund
    -0.07
    	pr
    -0.06
     طر
    -0.06
     батьків
    -0.06
     Common
    -0.06
     containers
    -0.06
    ubes
    -0.06
    ублі
    -0.06
    ở
    -0.06
    POSITIVE LOGITS
    .Authentication
    0.06
     matures
    0.06
     tyranny
    0.06
    ="{!!
    0.06
     суд
    0.06
    .typ
    0.06
    contrast
    0.06
     nuisance
    0.06
    liğini
    0.06
     nuanced
    0.06
    Act Density 0.006%

    No Known Activations