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

    Neuronpedia

    INDEX
    Explanations

    memory leaks or revolutionary effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.44
    l
    0.44
      
    0.43
     '
    0.43
    ,
    0.43
    t
    0.42
    1
    0.42
     .
    0.41
    ↵↵
    0.38
     of
    0.38
    POSITIVE LOGITS
     মুক্তিফৌজ
    0.58
     scrumptious
    0.48
     prépuce
    0.46
     яичко
    0.46
     hehe
    0.45
     cupcake
    0.45
     lucu
    0.44
     grosseur
    0.44
     سلاټ
    0.43
     কাহার
    0.43
    Act Density 0.000%

    No Known Activations