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

    Neuronpedia

    INDEX
    Explanations

    worrying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Xa
    -0.07
    骗局
    -0.07
    事务
    -0.07
    erea
    -0.07
     కేంద్ర
    -0.07
     acetate
    -0.07
     సిద్ధ
    -0.07
     firme
    -0.07
    édition
    -0.07
    ///↵↵
    -0.07
    POSITIVE LOGITS
     drills
    0.08
     drill
    0.08
    command
    0.08
    Manufacturer
    0.07
     दोनों
    0.07
     manufactures
    0.07
    pch
    0.07
     query
    0.07
     bends
    0.07
     Lumber
    0.07
    Act Density 0.000%

    No Known Activations