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

    Neuronpedia

    INDEX
    Explanations

    wormholes and theoretical physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     engraved
    -0.09
     mex
    -0.08
     Shoe
    -0.08
     Provincial
    -0.08
    拼
    -0.08
    buzz
    -0.08
     Shuffle
    -0.08
     Slider
    -0.08
     Dictionary
    -0.08
     Größe
    -0.07
    POSITIVE LOGITS
     positivity
    0.10
     destabil
    0.09
     looph
    0.09
     supportive
    0.09
     unstable
    0.08
     ADM
    0.08
     properties
    0.08
     violation
    0.08
     violations
    0.08
     stability
    0.08
    Act Density 0.001%

    No Known Activations