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

    Neuronpedia

    INDEX
    Explanations

    axis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confession
    -0.09
     confident
    -0.09
     unanimous
    -0.09
     terrific
    -0.09
     specialties
    -0.08
     зн
    -0.08
     elaborar
    -0.08
     savor
    -0.08
     uphold
    -0.08
     savoir
    -0.08
    POSITIVE LOGITS
     protr
    0.11
     movable
    0.11
     decals
    0.10
     Positioned
    0.10
    Dummy
    0.10
     translucent
    0.10
     Rigidbody
    0.10
     positioned
    0.09
     Dummy
    0.09
     decorative
    0.09
    Act Density 0.011%

    No Known Activations