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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lans
    -0.07
     Jas
    -0.07
     mediator
    -0.06
     negotiations
    -0.06
     Never
    -0.06
     Krish
    -0.06
     зам
    -0.06
     Sext
    -0.06
    ^K
    -0.06
    DISPLAY
    -0.06
    POSITIVE LOGITS
    database
    0.06
     counterfeit
    0.06
     прос
    0.06
    овые
    0.06
     مناطق
    0.06
    (numbers
    0.06
    questions
    0.06
    \Controllers
    0.06
     Swipe
    0.06
    .increment
    0.06
    Act Density 0.008%

    No Known Activations