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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages and AI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @Many
    -0.08
    (mid
    -0.08
    FER
    -0.07
    Washington
    -0.07
     skatt
    -0.07
    (stmt
    -0.07
     Ple
    -0.07
    istika
    -0.07
    드는
    -0.07
    (pack
    -0.07
    POSITIVE LOGITS
     chatbot
    0.11
    /chat
    0.11
    -assisted
    0.11
    -powered
    0.10
     chat
    0.10
     chatting
    0.10
     GPT
    0.10
     искус
    0.10
     artificial
    0.10
     artific
    0.10
    Act Density 0.026%

    No Known Activations