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

    Neuronpedia

    INDEX
    Explanations

    Keeping secrets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    异
    -0.06
    ीर
    -0.06
     Technician
    -0.06
     podstat
    -0.06
     круг
    -0.06
     SOP
    -0.06
     fires
    -0.06
     près
    -0.06
    銀行
    -0.06
    "",
    -0.06
    POSITIVE LOGITS
    libraries
    0.07
     Kotlin
    0.06
    ===========↵
    0.06
     repair
    0.06
     black
    0.06
    mainwindow
    0.06
     dietary
    0.06
    gress
    0.06
    main
    0.06
    0.06
    Act Density 0.128%

    No Known Activations