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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erne
    -0.07
    SPARENT
    -0.06
     tidal
    -0.06
    му
    -0.06
    /******/
    -0.06
    ερι
    -0.06
    erb
    -0.06
    ronics
    -0.06
    άντα
    -0.06
    SELF
    -0.06
    POSITIVE LOGITS
    /music
    0.07
     mất
    0.06
    *size
    0.06
     صور
    0.06
     Helpful
    0.06
    \Middleware
    0.06
     DIRECTORY
    0.06
    (Seq
    0.06
    (namespace
    0.06
    均
    0.06
    Act Density 0.031%

    No Known Activations