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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    弊
    -0.07
    Hi
    -0.07
    quelle
    -0.07
    合法权益
    -0.07
    ]{
    -0.07
    地區
    -0.07
    ?',↵
    -0.06
    Wei
    -0.06
    金币
    -0.06
    vard
    -0.06
    POSITIVE LOGITS
     uninsured
    0.08
     mouse
    0.07
    bed
    0.07
    �
    0.07
    );}
    0.07
    _logger
    0.07
     Schedule
    0.07
    -prev
    0.07
    Expanded
    0.07
    ELS
    0.07
    Act Density 0.003%

    No Known Activations