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

    Neuronpedia

    INDEX
    Explanations

    code syntax and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🚱
    0.39
     infrastrukt
    0.36
     użytk
    0.35
     unapolog
    0.34
    брита
    0.34
    acariy
    0.34
    流动
    0.33
    爱好者
    0.33
    ورٹی
    0.32
    财政
    0.31
    POSITIVE LOGITS
     =
    0.53
    ↵
    0.46
        
    0.43
    =
    0.41
     \\
    0.41
    end
    0.41
         
    0.40
     ;
    0.40
    becomes
    0.40
     \
    0.39
    Act Density 2.220%

    No Known Activations