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

    Neuronpedia

    INDEX
    Explanations

    references to social justice and humanitarian issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Christian compression stresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.59
    ="@+
    -0.49
    ########.
    -0.47
    fjspx
    -0.42
     flotante
    -0.42
     ujednoznacz
    -0.41
    NameInMap
    -0.41
    ViewImports
    -0.40
     zám
    -0.39
    adaptiveStyles
    -0.39
    POSITIVE LOGITS
    ایناق
    0.45
    ppert
    0.45
    çado
    0.45
    oval
    0.43
    secure
    0.42
     ID
    0.42
     Salta
    0.42
    FCM
    0.42
     unim
    0.42
     oce
    0.41
    Act Density 0.145%

    No Known Activations