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

    Neuronpedia

    INDEX
    Explanations

    pose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acupuncture
    -0.07
     breaking
    -0.06
    ENTRY
    -0.06
    Statistics
    -0.06
     ZeroConstructor
    -0.06
     initiative
    -0.06
     sco
    -0.06
    _BS
    -0.06
     result
    -0.06
    airy
    -0.06
    POSITIVE LOGITS
     poses
    0.08
     posing
    0.08
     Pose
    0.07
     pose
    0.07
     posed
    0.07
     OSError
    0.07
    텔
    0.07
     과정
    0.06
    =zeros
    0.06
    best
    0.06
    Act Density 0.007%

    No Known Activations