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

    Neuronpedia

    INDEX
    Explanations

    down regulation of emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pol
    0.87
     PI
    0.87
    pf
    0.85
     Pf
    0.85
     Pi
    0.82
    Pol
    0.82
     MPP
    0.78
    pol
    0.77
     Pim
    0.76
    PI
    0.75
    POSITIVE LOGITS
     downregulation
    1.27
    Down
    1.26
    DOWN
    1.23
    down
    1.23
     DOWN
    1.22
     down
    1.21
    downs
    1.19
     Down
    1.18
    Downward
    1.17
     downs
    1.08
    Act Density 2.574%

    No Known Activations