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

    Neuronpedia

    INDEX
    Explanations

    Controversial topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    retched
    -0.07
    ffield
    -0.07
     Gift
    -0.06
     Amanda
    -0.06
     лечения
    -0.06
     facets
    -0.06
     doğrult
    -0.06
    OND
    -0.06
     dozen
    -0.06
    LEY
    -0.06
    POSITIVE LOGITS
     Src
    0.07
    <Object
    0.07
     knex
    0.07
    -routing
    0.06
     gps
    0.06
    (slug
    0.06
    .filename
    0.06
    .Expressions
    0.06
     ])↵
    0.06
     meget
    0.06
    Act Density 0.124%

    No Known Activations