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

    Neuronpedia

    INDEX
    Explanations

    majority

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    웠
    -0.08
     charter
    -0.07
     mas
    -0.07
    친
    -0.07
     predictions
    -0.07
    ael
    -0.07
     insurers
    -0.07
    (rename
    -0.07
    に見
    -0.06
     Book
    -0.06
    POSITIVE LOGITS
     majority
    0.10
    陷
    0.07
     Spotify
    0.06
     LINUX
    0.06
    udden
    0.06
     Personality
    0.06
    \Block
    0.06
     Britt
    0.06
     Majority
    0.06
    quiry
    0.06
    Act Density 0.006%

    No Known Activations