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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    化合
    -0.07
     시
    -0.07
     зр
    -0.07
    .RegisterType
    -0.07
    (size
    -0.07
    _future
    -0.07
    (limit
    -0.06
    (ll
    -0.06
    ᎒
    -0.06
    Scale
    -0.06
    POSITIVE LOGITS
    /B
    0.07
    प
    0.07
    Showing
    0.06
    /st
    0.06
    讲故事
    0.06
     Gary
    0.06
     Butler
    0.06
    	actual
    0.06
    公安
    0.06
    ,status
    0.06
    Act Density 0.000%

    No Known Activations