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

    Neuronpedia

    INDEX
    Explanations

    chatbot answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    胖
    -0.08
    ,param
    -0.08
    obody
    -0.08
    ovar
    -0.07
    !!!!!!!!
    -0.07
    ↵		↵
    -0.07
    似
    -0.07
    disc
    -0.07
     statistically
    -0.07
     aforementioned
    -0.07
    POSITIVE LOGITS
     небольшой
    0.08
     नेपाली
    0.08
     नागरिक
    0.08
     जव
    0.08
     😊
    0.08
     Kana
    0.07
    ▼
    0.07
     Explanation
    0.07
     uitgebreide
    0.07
    Give
    0.07
    Act Density 0.040%

    No Known Activations