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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with lighting parameters

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

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.75
    StoryboardSegue
    -0.72
    ⓧ
    -0.62
     <<<<<<<<<<<<<<
    -0.59
    CppMethod
    -0.59
    ſelf
    -0.59
     ſta
    -0.58
     ProtoMessage
    -0.57
     MenuView
    -0.57
    cookieParser
    -0.57
    POSITIVE LOGITS
    atol
    0.30
    orkin
    0.28
    _|
    0.28
    plish
    0.28
    又不是
    0.28
    SequentialGroup
    0.27
    amount
    0.27
     صرف
    0.27
     verho
    0.26
    Quanto
    0.26
    Act Density 0.002%

    No Known Activations