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

    Neuronpedia

    INDEX
    Explanations

    If know that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lös
    0.60
     SOLUTIONS
    0.58
     solution
    0.57
    解决方案
    0.57
     Solutions
    0.56
    solution
    0.56
     solutions
    0.55
     решение
    0.54
     solução
    0.53
     SOLUTION
    0.53
    POSITIVE LOGITS
     penta
    0.43
     Esa
    0.42
     seaport
    0.38
     física
    0.38
     spade
    0.38
     arrow
    0.37
     At
    0.37
    ergic
    0.37
     Spade
    0.37
     secreto
    0.36
    Act Density 0.001%

    No Known Activations