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

    Neuronpedia

    INDEX
    Explanations

    medical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Loader
    -0.08
     node
    -0.07
     nodes
    -0.07
     relocate
    -0.07
    Socket
    -0.06
    ADDRESS
    -0.06
     villains
    -0.06
     Temper
    -0.06
     소개
    -0.06
     Talent
    -0.06
    POSITIVE LOGITS
    。この
    0.06
     HMS
    0.06
    _guard
    0.06
    пи
    0.06
    ีร
    0.05
     прави
    0.05
     schö
    0.05
     pound
    0.05
     ча
    0.05
     sû
    0.05
    Act Density 0.135%

    No Known Activations