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

    Neuronpedia

    INDEX
    Explanations

    Cabana, healthy workplace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     specie
    0.40
     acacia
    0.40
     ottim
    0.39
    ordia
    0.39
     species
    0.38
     ros
    0.38
     ROS
    0.38
     Rosie
    0.37
     desn
    0.37
     builders
    0.36
    POSITIVE LOGITS
     masculinity
    0.44
     Марафон
    0.41
     environments
    0.39
     河
    0.39
    皁
    0.39
    Cab
    0.38
     среды
    0.38
    धव
    0.38
    ঞ্জন
    0.38
     Comptroller
    0.38
    Act Density 0.001%

    No Known Activations