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

    Neuronpedia

    INDEX
    Explanations

    chatbot-related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chamadas
    -0.09
     !!↵↵
    -0.08
    Named
    -0.08
     يسمى
    -0.08
     !!!↵
    -0.07
     anus
    -0.07
    ICON
    -0.07
    STATIC
    -0.07
    abt
    -0.07
    .dict
    -0.07
    POSITIVE LOGITS
     जग
    0.10
    otlin
    0.09
     आश
    0.08
     bustling
    0.08
    כנולוג
    0.08
     begitu
    0.08
    �
    0.08
    0.08
     foremost
    0.08
    렇게
    0.08
    Act Density 0.041%
    No Known Activations