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

    Neuronpedia

    INDEX
    Explanations

    thrombosis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lat
    -0.06
     cafe
    -0.06
     Karen
    -0.06
    comput
    -0.06
    ิล
    -0.06
    重複重複
    -0.06
     فتح
    -0.06
     Gin
    -0.06
    eating
    -0.06
    ReLU
    -0.06
    POSITIVE LOGITS
    b
    0.08
     skills
    0.07
     проблемы
    0.06
    	        ↵
    0.06
     находится
    0.06
    bw
    0.06
    ▍▍▍▍
    0.06
     habil
    0.06
    Timeout
    0.06
     
↵
↵
    0.06
    Act Density 0.002%

    No Known Activations