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

    Neuronpedia

    INDEX
    Explanations

    AI chatbot conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    现金
    -0.08
     dekor
    -0.08
     quantities
    -0.08
     enterr
    -0.08
     verhuis
    -0.08
     arrested
    -0.07
    狠
    -0.07
    هن
    -0.07
    erren
    -0.07
    姓名
    -0.07
    POSITIVE LOGITS
     chatbot
    0.12
     GPT
    0.11
    GPT
    0.11
     вирту
    0.11
     programmed
    0.11
     linguistic
    0.10
     NLP
    0.10
     virtuelle
    0.10
     hypothetical
    0.09
    Helping
    0.09
    Act Density 0.051%

    No Known Activations