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
     quelque
    -0.07
     vehicles
    -0.07
     Hospitality
    -0.07
     Clubs
    -0.06
     sentiments
    -0.06
     đổ
    -0.06
     wohl
    -0.06
    /wiki
    -0.06
     seemed
    -0.06
     pracov
    -0.06
    POSITIVE LOGITS
    899
    0.06
    .onDestroy
    0.06
    빙
    0.06
    (run
    0.06
     бл
    0.06
    fetchAll
    0.06
    ore
    0.06
    握
    0.05
    อต
    0.05
    βέρ
    0.05
    Act Density 0.271%

    No Known Activations