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

    Neuronpedia

    INDEX
    Explanations

    text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .connection
    -0.07
    -election
    -0.06
     RETURN
    -0.06
    .voice
    -0.06
     літерату
    -0.06
     On
    -0.06
     ))
    -0.06
     cinemas
    -0.06
     on
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     aider
    0.07
    !↵↵
    0.07
     Chúa
    0.07
     así
    0.06
     MCP
    0.06
    055
    0.06
    ับต
    0.06
    优
    0.06
    INDER
    0.06
     свидетель
    0.06
    Act Density 0.000%

    No Known Activations