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

    Neuronpedia

    INDEX
    Explanations

    */

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     labelText
    -0.08
    何处
    -0.07
    �
    -0.07
     cocaine
    -0.07
     bán
    -0.07
    �
    -0.07
     GestureDetector
    -0.07
    可能性
    -0.07
    嘭
    -0.07
    筦
    -0.07
    POSITIVE LOGITS
    _REC
    0.07
    дрес
    0.07
    	sizeof
    0.06
     authoritative
    0.06
    coord
    0.06
    pts
    0.06
    肥
    0.06
     reader
    0.06
    SR
    0.06
     thước
    0.06
    Act Density 0.001%

    No Known Activations