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

    Neuronpedia

    INDEX
    Explanations

    3D dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     შესახებ
    1.04
     th
    1.02
     inac
    0.94
     thes
    0.92
     perched
    0.92
    Ná
    0.92
    othed
    0.90
     gab
    0.90
     levied
    0.87
     mediated
    0.86
    POSITIVE LOGITS
    rd
    3.62
    rds
    2.03
     rd
    2.02
    quarters
    2.00
     तलाक
    1.94
    RD
    1.94
    fourths
    1.77
    Rd
    1.76
    D
    1.69
     cheers
    1.57
    Act Density 0.195%

    No Known Activations