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

    Neuronpedia

    INDEX
    Explanations

    Crop circles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     widgets
    -0.09
     Widgets
    -0.08
    胸
    -0.08
     informative
    -0.08
     preorder
    -0.08
     implicitly
    -0.07
    advisor
    -0.07
     implicit
    -0.07
     valu
    -0.07
    /widgets
    -0.07
    POSITIVE LOGITS
     sightings
    0.13
     paranormal
    0.11
     unidentified
    0.11
     alleged
    0.11
     UFO
    0.11
    GPS
    0.10
     allegedly
    0.10
     unexpl
    0.10
     purported
    0.10
     vandal
    0.09
    Act Density 0.036%

    No Known Activations