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

    Neuronpedia

    INDEX
    Explanations

    dependence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     challenge
    -0.07
     Story
    -0.07
     convo
    -0.07
    ]]:↵
    -0.07
    .Closed
    -0.06
     stories
    -0.06
     BREAK
    -0.06
     vault
    -0.06
     Зав
    -0.06
     STORY
    -0.06
    POSITIVE LOGITS
     verbose
    0.07
     لدي
    0.07
     PhpStorm
    0.07
     GPI
    0.06
    Translation
    0.06
    λίου
    0.06
     Hundred
    0.06
    	margin
    0.06
     mesma
    0.06
     погляд
    0.06
    Act Density 0.000%

    No Known Activations