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

    Neuronpedia

    INDEX
    Explanations

    mailto

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uncomp
    -0.07
     öden
    -0.07
     Sims
    -0.06
     Doc
    -0.06
     Finger
    -0.06
    _SCALE
    -0.06
    .rooms
    -0.06
     Pathfinder
    -0.06
    _Parms
    -0.06
     SETUP
    -0.06
    POSITIVE LOGITS
     ����
    0.07
    大会
    0.07
     Velocity
    0.06
    Together
    0.06
     inward
    0.06
    213
    0.06
     specializing
    0.06
    \",\
    0.06
    .join
    0.06
    飲
    0.06
    Act Density 0.001%

    No Known Activations