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

    Neuronpedia

    INDEX
    Explanations

    Underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Axios
    -0.08
     Shar
    -0.07
    ✓
    -0.07
     parce
    -0.07
    ruise
    -0.07
     Rod
    -0.07
     racing
    -0.07
    utely
    -0.07
    Else
    -0.06
     lite
    -0.06
    POSITIVE LOGITS
    клон
    0.08
    (server
    0.07
     errorMessage
    0.07
    District
    0.07
    ทะ
    0.07
    这两个
    0.07
     Pages
    0.07
    icorn
    0.07
    level
    0.07
    rename
    0.06
    Act Density 0.037%

    No Known Activations