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

    Neuronpedia

    INDEX
    Explanations

    clothing/decoration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     　
    -0.06
     Spreadsheet
    -0.06
     diesen
    -0.06
    approve
    -0.06
    population
    -0.06
     appointed
    -0.06
    isty
    -0.06
    icerca
    -0.06
     genocide
    -0.06
    风险
    -0.06
    POSITIVE LOGITS
     Trucks
    0.07
    舌
    0.07
    :<
    0.07
     deserialize
    0.07
     konce
    0.07
    略
    0.07
    fork
    0.06
    findOrFail
    0.06
    atoes
    0.06
     rex
    0.06
    Act Density 0.130%

    No Known Activations