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

    Neuronpedia

    INDEX
    Explanations

    types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     observers
    -0.06
    술
    -0.06
    spring
    -0.06
    namespace
    -0.06
    .pop
    -0.06
     mills
    -0.06
     Overview
    -0.06
     Languages
    -0.06
    _username
    -0.06
     Burke
    -0.06
    POSITIVE LOGITS
     德
    0.08
    hattan
    0.08
     fleets
    0.07
    bound
    0.07
    \E
    0.07
    grams
    0.07
     EO
    0.07
     exhibiting
    0.07
    Networking
    0.06
    antee
    0.06
    Act Density 0.068%

    No Known Activations