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

    Neuronpedia

    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aku
    -0.07
     حمل
    -0.07
     mingle
    -0.06
     reconcile
    -0.06
     InputStreamReader
    -0.06
     scout
    -0.06
     tảng
    -0.06
    688
    -0.06
     Ya
    -0.06
     andere
    -0.06
    POSITIVE LOGITS
     Wikimedia
    0.07
     мож
    0.06
    思想
    0.06
    	bit
    0.06
    loc
    0.06
    modification
    0.06
     ابتد
    0.06
    .writeValue
    0.06
     Tested
    0.06
     clause
    0.06
    Act Density 0.042%

    No Known Activations