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

    Neuronpedia

    INDEX
    Explanations

    non-standard text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thems
    -0.07
    �江
    -0.07
    focused
    -0.07
    城市
    -0.06
    疆
    -0.06
    /logo
    -0.06
     krij
    -0.06
    puty
    -0.06
     Jerry
    -0.06
    >();↵↵
    -0.06
    POSITIVE LOGITS
     Sequence
    0.07
    ха
    0.06
    ตา
    0.06
     replace
    0.06
     '*',
    0.06
     USART
    0.06
     hoped
    0.06
     externally
    0.06
     computational
    0.06
     ","
    0.06
    Act Density 0.000%

    No Known Activations