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

    Neuronpedia

    INDEX
    Explanations

    liability and legal terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /CD
    -0.08
    /DD
    -0.07
    /colors
    -0.07
    -AS
    -0.07
    Exceptions
    -0.07
    .transparent
    -0.07
    .utcnow
    -0.07
    之外
    -0.07
    .INVISIBLE
    -0.07
    �翠
    -0.07
    POSITIVE LOGITS
    ↵    
↵
    0.09
    ↵    ↵    ↵
    0.09
     ↵    ↵
    0.09
    ↵    ↵
    0.09
    ↵    ↵↵
    0.08
    <|endoftext|>
    0.08
     çeşitli
    0.08
        ↵    ↵
    0.08
     تشمل
    0.08
    ।↵↵
    0.08
    Act Density 7.955%

    No Known Activations