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

    Neuronpedia

    INDEX
    Explanations

    references to power dynamics and societal structures related to race and authority

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

    associated with negativity or harm

    np_acts-logits-general · gemini-2.0-flash

    violence, hatred, racism, porn, deceit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imp
    -0.43
     accro
    -0.38
    CppMethod
    -0.36
     robust
    -0.35
     lol
    -0.34
     Parkes
    -0.34
     Autorizaciones
    -0.34
    原始内容存档于
    -0.34
    ModelAdmin
    -0.34
     fine
    -0.34
    POSITIVE LOGITS
    verwijspagina
    0.64
    tvguidetime
    0.56
     defaultstate
    0.56
    StoreMessageInfo
    0.49
    новниш
    0.44
    ValueStyle
    0.43
    NameInMap
    0.42
    Bibliograf
    0.42
     möjligt
    0.41
     المعيارى
    0.40
    Act Density 0.886%

    No Known Activations