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

    Neuronpedia

    INDEX
    Explanations

    falling or collapsing into inert positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marching
    0.44
     خانہ
    0.41
     cruising
    0.40
    Walking
    0.39
     constantemente
    0.39
     Walking
    0.39
     పెట్ట
    0.38
    觊
    0.38
    ikai
    0.37
    ioc
    0.37
    POSITIVE LOGITS
     prone
    1.12
     spraw
    1.02
     limp
    0.98
     inert
    0.96
     lifeless
    0.93
     sprawling
    0.92
    prone
    0.90
     sprawl
    0.87
     helpless
    0.87
     crumpled
    0.84
    Act Density 0.030%

    No Known Activations