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

    Neuronpedia

    INDEX
    Explanations

    applying QM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     )$
    0.42
     преду
    0.40
    Bottom
    0.39
     bottoms
    0.39
     முடிவு
    0.38
    べ
    0.38
     बहा
    0.38
     lastName
    0.37
    Chapter
    0.37
    姊
    0.36
    POSITIVE LOGITS
    viz
    0.42
    closing
    0.42
     closing
    0.41
     fech
    0.40
     reported
    0.40
     cierre
    0.40
     alongside
    0.39
    ritual
    0.39
     දු
    0.38
     चरित्र
    0.37
    Act Density 0.003%

    No Known Activations