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

    Neuronpedia

    INDEX
    Explanations

    multilingual data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -delay
    -0.07
    –
    -0.06
    ])↵↵
    -0.06
    /commons
    -0.06
        
↵    
↵
    -0.06
    (),
↵
    -0.06
    黎
    -0.06
    (players
    -0.06
    ;
↵
↵
↵
    -0.06
    modifier
    -0.06
    POSITIVE LOGITS
    .HeaderText
    0.07
    Intent
    0.07
    미
    0.06
    봉
    0.06
    迎
    0.06
    есс
    0.06
    Sorry
    0.06
    过去
    0.06
    ृत
    0.06
    _peak
    0.06
    Act Density 0.157%

    No Known Activations