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

    Neuronpedia

    INDEX
    Explanations

    physical state and size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dollari
    0.33
     devs
    0.32
     targets
    0.32
     and
    0.31
     playoffs
    0.31
     startups
    0.31
    queries
    0.30
     playlists
    0.30
     delves
    0.30
    X
    0.30
    POSITIVE LOGITS
     bodily
    0.48
     körper
    0.46
     शरीर
    0.45
    身體
    0.43
     physicality
    0.43
     શરીર
    0.43
    身体
    0.41
     శరీ
    0.40
     физи
    0.40
     physical
    0.40
    Act Density 0.001%

    No Known Activations