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

    Neuronpedia

    INDEX
    Explanations

    references to nobility and hierarchical titles

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __*/
    -0.46
     aikaa
    -0.44
     näytte
    -0.42
    oration
    -0.42
    :✨
    -0.41
    alyptus
    -0.40
     kyllä
    -0.39
    ounted
    -0.39
     المث
    -0.39
     kiệm
    -0.39
    POSITIVE LOGITS
    CppMethod
    0.56
    tonode
    0.49
    MessageTagHelper
    0.44
     ChromeDriver
    0.42
    fjspx
    0.40
    MethodManager
    0.39
    enumii
    0.39
     مشين
    0.38
    seguida
    0.37
    ReusableCell
    0.37
    Act Density 0.302%

    No Known Activations