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

    Neuronpedia

    INDEX
    Explanations

    dorsal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fed
    -0.07
     Elementary
    -0.07
    online
    -0.07
    新世纪
    -0.07
     أبريل
    -0.07
     sir
    -0.07
    	http
    -0.07
     Huawei
    -0.06
    pull
    -0.06
    _ld
    -0.06
    POSITIVE LOGITS
     growers
    0.07
    扶持
    0.07
    IVES
    0.07
     //!↵
    0.06
    igators
    0.06
     الاستثمار
    0.06
    /*↵↵
    0.06
    造纸
    0.06
    受众
    0.06
     Brushes
    0.06
    Act Density 0.001%

    No Known Activations