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

    Neuronpedia

    INDEX
    Explanations

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HSPB
    0.40
     বিষয়ে
    0.39
    DanhMucSP
    0.39
     Cartwright
    0.38
    ITHER
    0.38
    uerung
    0.38
    事的
    0.37
     বিষয়ে
    0.36
     মুক্তিফৌজ
    0.36
    睺
    0.36
    POSITIVE LOGITS
    ↵
    0.54
      
    0.41
    ↵↵
    0.39
    ↵↵↵
    0.39
    、
    0.39
    ;
    0.38
    x
    0.37
        
    0.37
         
    0.37
    新
    0.37
    Act Density 0.037%

    No Known Activations